© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 45523
    Prev
    Next
    INDEX
    Explanations

    component

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ub
    -0.07
     Prayer
    -0.06
    67
    -0.06
     PRINT
    -0.06
    ("'",
    -0.06
     discre
    -0.06
     fly
    -0.06
     target
    -0.06
     routed
    -0.06
    91
    -0.06
    POSITIVE LOGITS
    きた
    0.08
    ctp
    0.07
    /task
    0.07
    PyObject
    0.07
    /Card
    0.07
    šit
    0.07
     此
    0.07
    acs
    0.07
    며
    0.06
    compet
    0.06
    Activations Density 0.010%

    No Known Activations