Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 28680
    Prev
    Next
    INDEX
    Explanations

    options

    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
    .&
    -0.07
    альної
    -0.06
    (CType
    -0.06
    ERRU
    -0.06
    .chunk
    -0.06
     stirred
    -0.06
    ocio
    -0.06
     \:
    -0.06
    .Currency
    -0.06
    Những
    -0.06
    POSITIVE LOGITS
     Essentially
    0.07
    	ap
    0.07
     Pharmaceuticals
    0.07
     mag
    0.07
     Organizations
    0.07
    fern
    0.07
    _wrong
    0.07
    /weather
    0.06
    Brain
    0.06
    wine
    0.06
    Activations Density 0.000%

    No Known Activations