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. 9916
    Prev
    Next
    INDEX
    Explanations

    colon

    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
    _bm
    -0.07
    _Real
    -0.06
    “
    -0.06
    <LM
    -0.06
     дво
    -0.06
    Reverse
    -0.06
    declar
    -0.06
    Ya
    -0.06
    �
    -0.06
    ’B
    -0.06
    POSITIVE LOGITS
     touch
    0.07
    ILLA
    0.07
    ังก
    0.07
     origin
    0.06
     Costa
    0.06
    EXPECTED
    0.06
     emotional
    0.06
    ственные
    0.06
    oston
    0.06
     bufio
    0.06
    Activations Density 0.004%

    No Known Activations