© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 29620
    Prev
    Next
    INDEX
    Explanations

    contacting or legal information

    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_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
    Larry
    -0.08
     sham
    -0.07
     Larry
    -0.06
    시는
    -0.06
    wordpress
    -0.06
    朗
    -0.06
     Thy
    -0.06
     очеред
    -0.06
     pursue
    -0.06
    нин
    -0.06
    POSITIVE LOGITS
     guilt
    0.07
     emploi
    0.07
     velocidad
    0.06
     quoting
    0.06
    ........
    0.06
     Auth
    0.06
     дог
    0.06
    (dir
    0.06
    [min
    0.06
     authorize
    0.06
    Activations Density 0.000%

    No Known Activations