© 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. 11-RESID-POST-AA
    11. 41347
    Prev
    Next
    INDEX
    Explanations

    customer reviews

    np_max-act · gemini-2.0-flash

    The neuron fires on adjective stems conveying strong positive or superlative evaluations (e.g. “straordin-”, “eccezional-”, “immerg-”, “impecc-” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sluggish
    -0.08
     broader
    -0.07
     comet
    -0.07
     Sandy
    -0.07
    กต
    -0.07
     intelligent
    -0.07
    arest
    -0.06
     év
    -0.06
     native
    -0.06
     apartments
    -0.06
    POSITIVE LOGITS
    idUser
    0.06
    内の
    0.06
    ００
    0.06
    ザー
    0.06
    /c
    0.06
     Cob
    0.06
     zákaz
    0.06
     sourceMappingURL
    0.06
     정말
    0.06
    Fab
    0.06
    Activations Density 0.086%

    No Known Activations