© 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. 126292
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens containing decimal points (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
     wang
    -0.07
    axter
    -0.07
     Kı
    -0.06
    _gene
    -0.06
     suggestive
    -0.06
    _ary
    -0.06
     Diaz
    -0.05
     CCC
    -0.05
    azz
    -0.05
    _MAPPING
    -0.05
    POSITIVE LOGITS
    /find
    0.08
     мат
    0.07
     paid
    0.07
    /">
    0.07
    _PART
    0.07
     einmal
    0.07
    BILL
    0.07
     RAF
    0.07
    -machine
    0.06
    ultip
    0.06
    Activations Density 0.106%

    No Known Activations