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. 15-RESID-POST-AA
    6. 59678
    Prev
    Next
    INDEX
    Explanations

    square roots

    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
    "value
    -0.07
    }$/
    -0.07
     rhyth
    -0.07
    %</
    -0.06
    groupid
    -0.06
    '</
    -0.06
     plush
    -0.06
    Estado
    -0.06
    complexType
    -0.06
     Synthetic
    -0.06
    POSITIVE LOGITS
     bakery
    0.07
     conducts
    0.06
     làm
    0.06
     hence
    0.06
    _FAMILY
    0.06
     wow
    0.06
     lamb
    0.06
     available
    0.06
     amnesty
    0.06
     obliged
    0.06
    Activations Density 0.021%

    No Known Activations