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. 125590
    Prev
    Next
    INDEX
    Explanations

    scientific materials

    np_max-act · gemini-2.0-flash

    technical terms related to methods and apparatus in scientific research.

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

    The neuron detects mentions of physical substances or media (e.g. liquid, gas, medium, solution, material).

    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
     featured
    -0.07
     attractions
    -0.06
     summon
    -0.06
    张
    -0.06
     участ
    -0.06
    	Long
    -0.06
    CGPoint
    -0.06
    (ListNode
    -0.06
     rol
    -0.06
    .twimg
    -0.06
    POSITIVE LOGITS
    ;↵↵↵
    0.08
    );↵↵↵
    0.07
     *
    0.06
    ↵↵↵
    0.06
    ाहक
    0.06
     ")↵
    0.06
    ,↵↵
    0.06
    (newValue
    0.06
     midst
    0.06
     PTR
    0.06
    Activations Density 0.113%

    No Known Activations