© 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. 3-RESID-POST-AA
    6. 94168
    Prev
    Next
    INDEX
    Explanations

    depressed

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .loadtxt
    -0.06
     много
    -0.06
     incorrectly
    -0.06
    _vel
    -0.06
     shielding
    -0.06
     WM
    -0.06
     harvesting
    -0.06
     glyph
    -0.06
     Commod
    -0.06
    ektor
    -0.06
    POSITIVE LOGITS
     depressed
    0.31
    pressed
    0.10
     unemployed
    0.10
     obese
    0.09
     despair
    0.09
     oppressed
    0.08
     distressed
    0.07
    眠
    0.07
    RESSED
    0.07
     setEmail
    0.07
    Activations Density 0.002%

    No Known Activations