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. 23-RESID-POST-AA
    6. 104015
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auge
    -0.07
    apus
    -0.06
     pantry
    -0.06
     Invasion
    -0.06
    犯
    -0.06
     Close
    -0.06
    nothing
    -0.06
     interacting
    -0.06
     endwhile
    -0.06
    wu
    -0.06
    POSITIVE LOGITS
     vrch
    0.08
     ≠
    0.07
    .EqualTo
    0.07
    ovny
    0.07
     Eigen
    0.07
    along
    0.07
    _EQUALS
    0.06
    .strip
    0.06
     Middleware
    0.06
    _ray
    0.06
    Activations Density 0.001%

    No Known Activations