© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 52991
    Prev
    Next
    INDEX
    Explanations

    of

    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
    “But
    -0.07
     Erin
    -0.07
     CHARACTER
    -0.07
    —but
    -0.06
    ,in
    -0.06
    In
    -0.06
    MERCHANTABILITY
    -0.06
    “In
    -0.06
     However
    -0.06
    "In
    -0.06
    POSITIVE LOGITS
     of
    0.07
    ?v
    0.07
    ande
    0.07
    кого
    0.07
    ='',↵
    0.07
    DC
    0.07
    _'
    0.07
     numberOf
    0.07
     或
    0.07
    of
    0.07
    Activations Density 0.047%

    No Known Activations