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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92539
    Prev
    Next
    INDEX
    Explanations

    short

    np_max-act · gemini-2.0-flash

    The neuron fires on the little decimal numbers (e.g. “3.55078125,” “0.29736328125,” etc.) that specify length or formatting constraints in the user’s prompt.

    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
    ＿
    -0.07
    _%
    -0.07
    dea
    -0.07
    ]*(
    -0.07
    -columns
    -0.07
     Minimal
    -0.07
     роз
    -0.06
    ัพย
    -0.06
     Damage
    -0.06
     Prozent
    -0.06
    POSITIVE LOGITS
     trilogy
    0.06
    .Adam
    0.06
    _JUMP
    0.06
     меропри
    0.06
     directors
    0.06
    .black
    0.06
    _HC
    0.06
     advertisements
    0.06
     pinned
    0.06
     Veranst
    0.06
    Activations Density 0.010%

    No Known Activations