© 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. 89914
    Prev
    Next
    INDEX
    Explanations

    what is available

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on Spanish phrasing that describes what something “has to offer” (e.g. tokens around “tiene para ofrecer”).

    oai_token-act-pair · o4-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
     crossings
    -0.07
    uş
    -0.07
    findOrFail
    -0.07
    .Cell
    -0.06
    FAIL
    -0.06
     Wants
    -0.06
     VO
    -0.06
    |min
    -0.06
     desired
    -0.06
    HIGH
    -0.06
    POSITIVE LOGITS
     Wrestle
    0.07
     보내
    0.07
     Sicher
    0.07
     resembl
    0.06
     eliminating
    0.06
     сказала
    0.06
     offering
    0.06
     loaded
    0.06
     hóa
    0.06
    wingConstants
    0.06
    Activations Density 0.016%

    No Known Activations