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. 93584
    Prev
    Next
    INDEX
    Explanations

    president

    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
    =set
    -0.07
     stance
    -0.06
    (delegate
    -0.06
    .ToTable
    -0.06
    。お
    -0.06
    .dark
    -0.06
    otec
    -0.06
    posing
    -0.06
    �
    -0.06
    _working
    -0.06
    POSITIVE LOGITS
    /data
    0.08
    Sher
    0.07
    让我
    0.07
    .FromResult
    0.06
    erator
    0.06
    "]->
    0.06
    Em
    0.06
    /cal
    0.06
     Rew
    0.06
    Wil
    0.06
    Activations Density 0.013%

    No Known Activations