© 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
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 95474
    Prev
    Next
    INDEX
    Explanations

    least

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _SCL
    -0.07
    _W
    -0.07
     erb
    -0.06
     Sark
    -0.06
     ц
    -0.06
    _wc
    -0.06
     soukrom
    -0.06
    SUB
    -0.06
    ücret
    -0.06
    ظˆ
    -0.05
    POSITIVE LOGITS
     Least
    0.13
     least
    0.12
    Least
    0.12
    least
    0.09
    AST
    0.08
     accounts
    0.08
     Accounts
    0.07
    Well
    0.07
     societal
    0.07
    THIS
    0.07
    Activations Density 0.002%

    No Known Activations