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. 3-RESID-POST-AA
    6. 95015
    Prev
    Next
    INDEX
    Explanations

    Institute

    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
    969
    -0.07
    ’all
    -0.07
     продолж
    -0.06
    Pag
    -0.06
     companions
    -0.06
    okud
    -0.06
    	aux
    -0.06
     vivo
    -0.06
    ayas
    -0.06
    _PRIV
    -0.06
    POSITIVE LOGITS
     Institute
    0.31
     institute
    0.17
    STITUTE
    0.16
     Institution
    0.14
    stitute
    0.13
     Inst
    0.11
     Instit
    0.11
     Initiative
    0.10
     Institut
    0.08
     Islands
    0.08
    Activations Density 0.005%

    No Known Activations