© 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. 126584
    Prev
    Next
    INDEX
    Explanations

    casino/lottery game strategies

    np_max-act · gemini-2.0-flash

    The neuron detects structural and formatting markers in the text—things like header delimiters (e.g. `<|start_header_id|>`, `<|end_header_id|>`), end-of-text tags (`<|eot_id|>`), and list/numbering tokens.

    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
    ographer
    -0.07
     playoffs
    -0.07
     Agriculture
    -0.06
    _userid
    -0.06
    lookup
    -0.06
    iquer
    -0.06
    cepts
    -0.06
    acency
    -0.06
     player
    -0.06
     Bennett
    -0.06
    POSITIVE LOGITS
    였
    0.07
    圍
    0.07
    CONT
    0.06
    �
    0.06
     hbox
    0.06
    층의
    0.06
    	BOOST
    0.06
     꼭
    0.06
    .getLabel
    0.06
    遊
    0.06
    Activations Density 0.026%

    No Known Activations