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. 128978
    Prev
    Next
    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    information related to football players and their careers.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on the “Category” label (i.e. the wiki category lines at the bottom of an article).

    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
    .Points
    -0.07
    LEX
    -0.07
     partager
    -0.06
     wider
    -0.06
    род
    -0.06
    ffmpeg
    -0.06
    PRE
    -0.06
    tempts
    -0.06
     Modified
    -0.06
     profound
    -0.06
    POSITIVE LOGITS
     كرة
    0.07
     zase
    0.06
     نقشه
    0.06
    _hook
    0.06
     Pakistani
    0.06
     hâl
    0.06
    _VALIDATE
    0.06
     doma
    0.06
     comput
    0.06
    онь
    0.06
    Activations Density 0.009%

    No Known Activations