Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 43699
    Prev
    Next
    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash

    chemical compounds with varying charge states.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on numeric tokens representing floating-point numbers with decimal points.

    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
     свид
    -0.07
     leftist
    -0.06
     unleashed
    -0.06
    Univers
    -0.06
     turf
    -0.06
     hội
    -0.06
     incomes
    -0.06
     lifecycle
    -0.06
    Pag
    -0.06
     unanswered
    -0.06
    POSITIVE LOGITS
         ↵↵
    0.07
    \Url
    0.06
    (states
    0.06
    $string
    0.06
    =UTF
    0.06
    .getClass
    0.06
    [args
    0.06
    commit
    0.06
    سل
    0.06
    /simple
    0.06
    Activations Density 0.003%

    No Known Activations