© 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. 33905
    Prev
    Next
    INDEX
    Explanations

    ra

    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
     creed
    -0.07
    (Y
    -0.06
     ;-
    -0.06
    .GONE
    -0.06
     versch
    -0.06
    charged
    -0.06
    "s
    -0.06
    _when
    -0.06
    _msg
    -0.06
     Sudoku
    -0.06
    POSITIVE LOGITS
    ategori
    0.07
    ина
    0.07
    ่วย
    0.07
    ención
    0.06
    ACTER
    0.06
    aturity
    0.06
     ürün
    0.06
     equipos
    0.06
     Representatives
    0.06
    част
    0.06
    Activations Density 0.000%

    No Known Activations