© 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. 7-RESID-POST-AA
    11. 118540
    Prev
    Next
    INDEX
    Explanations

    quantity or significance

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trộn
    -0.07
    (transform
    -0.07
    _FAST
    -0.07
    )//
    -0.06
    ujet
    -0.06
    %.↵
    -0.06
    ικών
    -0.06
    })
    -0.06
     �
    -0.06
    ][/
    -0.06
    POSITIVE LOGITS
     claiming
    0.07
     言
    0.07
     foremost
    0.07
     immac
    0.07
     elo
    0.07
    verbose
    0.06
     renting
    0.06
     мати
    0.06
    自動
    0.06
    既
    0.06
    Activations Density 0.006%

    No Known Activations