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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 91186
    Prev
    Next
    INDEX
    Explanations

    ellipsis

    np_max-act · gemini-2.0-flash

    The neuron is especially sensitive to ellipsis tokens (strings of three or more consecutive dots, e.g. “…”) throughout the text.

    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
    enerative
    -0.07
     tether
    -0.07
     tier
    -0.07
     Централь
    -0.07
     kem
    -0.07
    _reg
    -0.07
     nec
    -0.07
     sulfate
    -0.07
     cartel
    -0.07
     eligibility
    -0.06
    POSITIVE LOGITS
     "...
    0.08
    (...
    0.08
    …………………………………………
    0.07
    ................................................................
    0.07
     �
    0.07
    ,…
    0.07
    ...
    0.07
     “…
    0.07
    dispatch
    0.07
     Franco
    0.07
    Activations Density 0.033%

    No Known Activations