© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91915
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron activates on quotation marks and the words or phrases enclosed in them, effectively identifying quoted expressions.

    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
     Femin
    -0.07
     Sala
    -0.07
    -collar
    -0.07
    "":
    -0.07
    }\"
    -0.07
    carousel
    -0.07
    _al
    -0.07
    梨
    -0.06
    Bal
    -0.06
     `"
    -0.06
    POSITIVE LOGITS
    equipment
    0.07
     OPS
    0.06
     Costs
    0.06
    (S
    0.06
     rem
    0.06
     Expenses
    0.06
     IEntity
    0.06
     Entity
    0.06
    good
    0.06
     Weinstein
    0.06
    Activations Density 0.037%

    No Known Activations