Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 110009
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron fires on interrogative cue words (e.g. “what,” “when,” “how,” etc.).

    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
     fences
    -0.07
    etak
    -0.07
     ants
    -0.07
    cmpeq
    -0.06
     Stir
    -0.06
    ixedReality
    -0.06
    amed
    -0.06
     multitude
    -0.06
    onte
    -0.06
     melt
    -0.06
    POSITIVE LOGITS
     Convenient
    0.06
    \',
    0.06
    ?',
    0.06
    usher
    0.06
     def
    0.06
    SAN
    0.05
     sonrası
    0.05
     solving
    0.05
     Güven
    0.05
    "%
    0.05
    Activations Density 0.050%

    No Known Activations