Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 122897
    Prev
    Next
    INDEX
    Explanations

    bar

    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
    sequent
    -0.06
     mij
    -0.06
    tahun
    -0.06
    :B
    -0.06
    αιο
    -0.06
     confort
    -0.06
     NO
    -0.06
    *v
    -0.06
    HI
    -0.06
    539
    -0.06
    POSITIVE LOGITS
     bar
    0.20
     bars
    0.11
    -bar
    0.11
    -Bar
    0.08
     BAR
    0.08
    erver
    0.08
    BAR
    0.07
    _Bar
    0.07
     Bars
    0.07
    obar
    0.07
    Activations Density 0.008%

    No Known Activations