© 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. 11-RESID-POST-AA
    6. 105410
    Prev
    Next
    INDEX
    Explanations

    -t

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chlor
    -0.07
    ands
    -0.07
     �
    -0.06
     effortlessly
    -0.06
     Myanmar
    -0.06
    _theta
    -0.06
    ams
    -0.06
    PLOY
    -0.06
     Sud
    -0.06
    glich
    -0.06
    POSITIVE LOGITS
     gün
    0.07
     getConnection
    0.07
    9
    0.06
     bian
    0.06
     god
    0.06
    (pk
    0.06
    'nde
    0.06
     stato
    0.06
    -xs
    0.06
     """.
    0.06
    Activations Density 0.050%

    No Known Activations