© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6781
    Prev
    Next
    INDEX
    Explanations

    computational

    np_max-act · gemini-2.0-flash

    The neuron peaks on tokens about computational cost or resource use (e.g. “computational,” “computing,” “power,” “resources”), i.e. mentions of computing requirements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions about advancements and challenges in natural language processing technologies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orthy
    -0.07
    610
    -0.06
    _lahir
    -0.06
    ITIZE
    -0.06
     UCHAR
    -0.06
    .readFileSync
    -0.06
    орош
    -0.06
     pigment
    -0.06
    subtype
    -0.06
    750
    -0.06
    POSITIVE LOGITS
     computational
    0.09
     Computational
    0.08
    forth
    0.07
     dataSnapshot
    0.07
     Capital
    0.07
    .vm
    0.07
    .Cap
    0.06
     몰
    0.06
     adım
    0.06
     implic
    0.06
    Activations Density 0.004%

    No Known Activations