© 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. 3-RESID-POST-AA
    6. 94072
    Prev
    Next
    INDEX
    Explanations

    mg

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ционный
    -0.07
     Moff
    -0.07
     keyof
    -0.06
    inz
    -0.06
     constituency
    -0.06
    ,current
    -0.06
     dere
    -0.06
     spit
    -0.06
    .↵↵↵↵↵
    -0.06
    Convertible
    -0.06
    POSITIVE LOGITS
     mg
    0.07
     Owens
    0.07
    นใจ
    0.07
    Throw
    0.07
     있
    0.06
    ByteArray
    0.06
     align
    0.06
     Validate
    0.06
     ob
    0.06
     freshness
    0.06
    Activations Density 0.008%

    No Known Activations