© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89711
    Prev
    Next
    INDEX
    Explanations

    molecules

    np_max-act · gemini-2.0-flash

    The neuron is detecting numerical measurements expressed as decimal or fractional values.

    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
     ();↵↵
    -0.06
    Database
    -0.06
     結
    -0.06
     carbonate
    -0.06
    bing
    -0.06
     expertise
    -0.06
    "`
    -0.06
    记
    -0.06
     أر
    -0.06
    rate
    -0.06
    POSITIVE LOGITS
     strtoupper
    0.08
    .tcp
    0.07
    toMatchSnapshot
    0.06
     maior
    0.06
    TreeNode
    0.06
     politik
    0.06
    south
    0.06
    ropolitan
    0.06
     afr
    0.06
    cmath
    0.06
    Activations Density 0.101%

    No Known Activations