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

    Neuronpedia

    Jacobian LensNEW
    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. 38142
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron flags CSS measurement tokens (numbers with units, e.g. “2px,” “300px,” 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
     дис
    -0.07
    particularly
    -0.07
    526
    -0.07
    gfx
    -0.06
    (static
    -0.06
     اتفاق
    -0.06
    аксим
    -0.06
     ideals
    -0.06
     Serialization
    -0.06
    971
    -0.06
    POSITIVE LOGITS
    ividual
    0.07
    RequestId
    0.07
    buy
    0.06
    _cid
    0.06
    WindowState
    0.06
     Relief
    0.06
     bel
    0.06
    řeb
    0.06
     �
    0.06
     huy
    0.06
    Activations Density 0.012%

    No Known Activations