© 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. 7-RESID-POST-AA
    6. 9667
    Prev
    Next
    INDEX
    Explanations

    code or instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lix
    -0.07
    sahuje
    -0.07
     Russo
    -0.07
    訴
    -0.07
    Buy
    -0.07
    acemark
    -0.07
    141
    -0.07
     Six
    -0.06
     vystav
    -0.06
     imprisoned
    -0.06
    POSITIVE LOGITS
     "=",
    0.06
     دی
    0.06
     Kathryn
    0.06
     ZeroConstructor
    0.06
    ário
    0.06
     šp
    0.06
    alph
    0.06
     конт
    0.06
    798
    0.06
    -'.$
    0.06
    Activations Density 0.254%

    No Known Activations