© 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. 90973
    Prev
    Next
    INDEX
    Explanations

    ability or possibility

    np_max-act · gemini-2.0-flash

    The neuron flags the common interruption cue “Before I could say anything,” – i.e. the phrase marking that the speaker is cut off.

    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
     microscopy
    -0.07
    Retail
    -0.07
     hành
    -0.07
     edilmiştir
    -0.06
    playing
    -0.06
    аном
    -0.06
    hledem
    -0.06
     Dear
    -0.06
    Shop
    -0.06
     ppt
    -0.06
    POSITIVE LOGITS
    .lab
    0.08
     REC
    0.06
     Polic
    0.06
     vaping
    0.06
     drei
    0.06
    asticsearch
    0.06
    315
    0.06
    +',
    0.06
    (raw
    0.06
    .arch
    0.06
    Activations Density 0.008%

    No Known Activations