© 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. 19-RESID-POST-AA
    11. 53845
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Е
    -0.07
    =C
    -0.07
     overflowing
    -0.07
     phosph
    -0.07
    	setState
    -0.07
     EPS
    -0.07
    ----------------------------------------------------------------------------
    -0.06
    _ENC
    -0.06
     sunday
    -0.06
    ampling
    -0.06
    POSITIVE LOGITS
    ंड
    0.07
     металли
    0.06
    .za
    0.06
    iliği
    0.06
    bat
    0.06
     conoc
    0.06
     사망
    0.06
    樓
    0.06
     생각
    0.06
     prům
    0.06
    Activations Density 0.200%

    No Known Activations