© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 18440
    Prev
    Next
    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    The neuron is selectively activating on numeric constants (integer or floating‐point values) in configuration‐style text.

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

    texture-related settings and parameters.

    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
    .binary
    -0.07
     बच
    -0.07
     defiance
    -0.07
    :$
    -0.06
     Went
    -0.06
     fourth
    -0.06
    ava
    -0.06
     ledger
    -0.06
                  
    -0.06
    [Y
    -0.06
    POSITIVE LOGITS
    queues
    0.07
    énom
    0.06
    -org
    0.06
    Ash
    0.06
    TG
    0.06
    OMET
    0.06
     aqu
    0.06
    WH
    0.06
    ViewItem
    0.06
    otonin
    0.06
    Activations Density 0.018%

    No Known Activations