© 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. 88892
    Prev
    Next
    INDEX
    Explanations

    Sporting competitions

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to numeric tokens with decimal fractions (i.e. floating-point numbers).

    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
     Intr
    -0.07
    _phr
    -0.07
     Plum
    -0.07
     boiling
    -0.06
    .Short
    -0.06
    _tc
    -0.06
    _lt
    -0.06
    _Variable
    -0.06
     характеристики
    -0.06
    ”).
    -0.06
    POSITIVE LOGITS
    aryana
    0.07
     teaspoon
    0.07
     implementing
    0.07
    ificação
    0.07
    为什么
    0.06
     readable
    0.06
    เทศ
    0.06
    asters
    0.06
    afone
    0.06
    atego
    0.06
    Activations Density 0.064%

    No Known Activations