© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126023
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron fires on string literals that look like HTTP API endpoint paths (i.e. slash-prefixed URL/path segments).

    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
    lowest
    -0.07
    _cache
    -0.06
    _fast
    -0.06
    OWN
    -0.06
    Listen
    -0.06
    �
    -0.06
    heck
    -0.06
    殺
    -0.06
    RSS
    -0.06
    "One
    -0.06
    POSITIVE LOGITS
      ↵
    0.08
    ?↵
    0.07
    _modal
    0.07
    .ContentType
    0.06
     visuals
    0.06
     urllib
    0.06
     mük
    0.06
     Material
    0.06
    	ArrayList
    0.06
    概
    0.06
    Activations Density 0.010%

    No Known Activations