© 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. 15-RESID-POST-AA
    6. 6174
    Prev
    Next
    INDEX
    Explanations

    divisor

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     freaking
    -0.07
     Salman
    -0.07
     vamos
    -0.07
     здоров
    -0.06
     수상
    -0.06
    кового
    -0.06
    قية
    -0.06
    damn
    -0.06
    북도
    -0.06
     podemos
    -0.06
    POSITIVE LOGITS
    ewe
    0.07
    ้น
    0.07
    #/
    0.07
     xr
    0.07
    .Sign
    0.07
    .Keys
    0.06
    dp
    0.06
     når
    0.06
     stagger
    0.06
    .Anchor
    0.06
    Activations Density 0.000%

    No Known Activations