Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19103
    Prev
    Next
    INDEX
    Explanations

    cast

    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
     Qui
    -0.08
    .si
    -0.06
     LB
    -0.06
    Alle
    -0.06
    BAD
    -0.06
     Built
    -0.06
    570
    -0.06
     symmetry
    -0.06
     آثار
    -0.06
    792
    -0.06
    POSITIVE LOGITS
     Comcast
    0.15
     untranslated
    0.08
     fibers
    0.07
    وقيت
    0.07
     Except
    0.07
     broadcasting
    0.07
     skyline
    0.07
     McMahon
    0.07
     Spectrum
    0.06
    pectrum
    0.06
    Activations Density 0.002%

    No Known Activations