© 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. 19-RESID-POST-AA
    6. 35317
    Prev
    Next
    INDEX
    Explanations

    software documentation/usage

    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
     важно
    -0.07
    healthy
    -0.06
     least
    -0.06
    %,
    -0.06
    			
    ↵			
    ↵
    -0.06
    ynchronization
    -0.06
    єте
    -0.06
     realistically
    -0.06
    幅
    -0.06
     zdroj
    -0.06
    POSITIVE LOGITS
    .datas
    0.07
    .Auto
    0.06
    ubbles
    0.06
    อท
    0.06
     orderby
    0.06
    [type
    0.06
    Listeners
    0.06
    UNDLE
    0.06
    _LAYER
    0.06
     skyline
    0.06
    Activations Density 0.304%

    No Known Activations