© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110347
    Prev
    Next
    INDEX
    Explanations

    brief

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “brief,” i.e. occurrences of “brief” (as in “on brief”) in legal‐document contexts.

    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
    सन
    -0.07
     incorpor
    -0.06
    647
    -0.06
     письмен
    -0.06
    롱
    -0.06
    EI
    -0.06
     memberId
    -0.06
     εί
    -0.06
    766
    -0.06
     внимание
    -0.06
    POSITIVE LOGITS
    (outputs
    0.07
     witnessed
    0.06
     langue
    0.06
     mRNA
    0.06
     různé
    0.06
     unsigned
    0.06
    ($)
    0.06
    $v
    0.06
    reate
    0.06
    AndHashCode
    0.06
    Activations Density 0.001%

    No Known Activations