© 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. 125156
    Prev
    Next
    INDEX
    Explanations

    =True

    np_max-act · gemini-2.0-flash

    The neuron detects metadata or control tokens (e.g. header and delimiter markers) rather than regular content words.

    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
     soph
    -0.07
    (players
    -0.07
    setImage
    -0.06
     BL
    -0.06
     зап
    -0.06
    鼠
    -0.06
     paradox
    -0.06
    راق
    -0.06
    \db
    -0.06
     balk
    -0.06
    POSITIVE LOGITS
    =True
    0.08
    secured
    0.07
    -zA
    0.07
    )))
    0.07
    enerima
    0.07
    ]):
↵
    0.07
    )↵↵↵↵↵↵↵↵
    0.07
    hana
    0.07
    .Equals
    0.06
    =B
    0.06
    Activations Density 0.006%

    No Known Activations