© 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. 25068
    Prev
    Next
    INDEX
    Explanations

    classification

    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
    iej
    -0.07
    uden
    -0.07
    mak
    -0.07
    .NAME
    -0.06
    chos
    -0.06
    .done
    -0.06
     decipher
    -0.06
    ANCELED
    -0.06
     být
    -0.06
     Như
    -0.06
    POSITIVE LOGITS
    색
    0.07
     휴
    0.07
    rounded
    0.07
     suitability
    0.07
     superheroes
    0.07
    licence
    0.07
     outward
    0.07
     grou
    0.06
    orestation
    0.06
     Douglas
    0.06
    Activations Density 0.004%

    No Known Activations