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. 19-RESID-POST-AA
    6. 9754
    Prev
    Next
    INDEX
    Explanations

    learning and adjustments

    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
     can
    -0.09
     will
    -0.08
     Would
    -0.07
     would
    -0.07
     may
    -0.07
    수를
    -0.07
     Î
    -0.07
     doesn
    -0.07
     bott
    -0.07
     pierws
    -0.06
    POSITIVE LOGITS
    /frame
    0.06
    thag
    0.06
     honesty
    0.06
    /man
    0.06
     Profile
    0.06
    ldkf
    0.06
     acclaim
    0.06
    stash
    0.06
    ια
    0.06
    (copy
    0.06
    Activations Density 0.231%

    No Known Activations