© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 46110
    Prev
    Next
    INDEX
    Explanations

    said

    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
    =current
    -0.06
     ventana
    -0.06
     UB
    -0.06
    cran
    -0.06
    -tests
    -0.06
     lub
    -0.06
     tu
    -0.06
    ÇÃO
    -0.06
     timings
    -0.06
     condiciones
    -0.06
    POSITIVE LOGITS
     say
    0.15
     saying
    0.14
     SAY
    0.13
     says
    0.12
     said
    0.12
     Say
    0.12
    said
    0.10
    Say
    0.10
     Saying
    0.10
    say
    0.10
    Activations Density 0.093%

    No Known Activations