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. 129578
    Prev
    Next
    INDEX
    Explanations

    movies

    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
    ایر
    -0.07
     Allah
    -0.07
    duck
    -0.06
    бол
    -0.06
    airie
    -0.06
     elk
    -0.06
     Som
    -0.06
    ibern
    -0.06
    DOC
    -0.06
      
    -0.06
    POSITIVE LOGITS
     lamp
    0.06
     alphabet
    0.06
    ically
    0.06
     Film
    0.06
     waveform
    0.06
    TEGER
    0.06
     simil
    0.06
    Balance
    0.06
     Wanted
    0.05
    Leap
    0.05
    Activations Density 0.086%

    No Known Activations