© 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
    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. 12947
    Prev
    Next
    INDEX
    Explanations

    Searching

    np_max-act · gemini-2.0-flash

    The neuron selectively lights up on words and phrases signaling a search or inquiry—terms like “hope,” “finding,” “who could explain,” and “what”—i.e. language around looking for information or answers.

    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
     отд
    -0.07
    mach
    -0.06
    Seattle
    -0.06
     Ply
    -0.06
    -city
    -0.06
    .fixed
    -0.06
     reprodu
    -0.06
     Basil
    -0.06
    _ref
    -0.06
     Prel
    -0.06
    POSITIVE LOGITS
    ?↵↵
    0.07
     "'",
    0.06
    ाइल
    0.06
    .).↵↵
    0.06
    웨어
    0.06
     خلال
    0.06
    restore
    0.06
    quire
    0.06
    arshal
    0.06
    gone
    0.06
    Activations Density 0.039%

    No Known Activations