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. 7-RESID-POST-AA
    6. 72250
    Prev
    Next
    INDEX
    Explanations

    Actions and processes

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _column
    -0.06
    .additional
    -0.06
    -sensitive
    -0.06
     aktual
    -0.06
    kle
    -0.06
    онах
    -0.06
     tun
    -0.06
    ead
    -0.06
    Œ
    -0.06
    ail
    -0.06
    POSITIVE LOGITS
    براهيم
    0.07
     Shirley
    0.06
    refixer
    0.06
     whore
    0.06
     CORPORATION
    0.06
     spur
    0.06
     CLIIIK
    0.06
    ehr
    0.06
    .makedirs
    0.06
    _rt
    0.06
    Activations Density 0.807%

    No Known Activations