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. 11-RESID-POST-AA
    6. 88432
    Prev
    Next
    INDEX
    Explanations

    beads

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ('/')↵
    -0.08
    787
    -0.07
     July
    -0.07
     Mitch
    -0.07
     AngularFire
    -0.07
    _TOP
    -0.07
     motto
    -0.07
    .lucene
    -0.07
    .Environment
    -0.06
    Lim
    -0.06
    POSITIVE LOGITS
     beads
    0.11
     bead
    0.08
    额
    0.08
     pearls
    0.08
     pearl
    0.07
     переда
    0.07
     peasants
    0.07
    _basis
    0.07
    Ele
    0.07
     bureaucrats
    0.07
    Activations Density 0.005%

    No Known Activations