© 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. 73647
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
     السي
    -0.07
    zem
    -0.06
     )"
    -0.06
    )++;↵
    -0.06
    існо
    -0.06
    ictory
    -0.06
    aw
    -0.06
     ako
    -0.06
    	 ↵
    -0.06
    _arrays
    -0.06
    POSITIVE LOGITS
    _UNDER
    0.07
     GIR
    0.07
    Messaging
    0.06
     nive
    0.06
     neoliberal
    0.06
    FS
    0.06
     famil
    0.06
    were
    0.06
    acing
    0.06
    _CAPTURE
    0.06
    Activations Density 0.004%

    No Known Activations