© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 41704
    Prev
    Next
    INDEX
    Explanations

    microbiology

    np_max-act · gemini-2.0-flash

    terms related to hair removal methods and treatments.

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

    The neuron activates for occurrences of the word “flea” (and its variants), i.e. mentions of fleas.

    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
     Component
    -0.07
     userid
    -0.07
     he
    -0.07
     "\\
    -0.07
    (no
    -0.07
     preferences
    -0.06
    马
    -0.06
     wines
    -0.06
     Ideas
    -0.06
     bananas
    -0.06
    POSITIVE LOGITS
     accordingly
    0.08
     Anglo
    0.07
    _BOUNDS
    0.07
     الموقع
    0.06
    Slf
    0.06
     분
    0.06
    reopen
    0.06
    ζα
    0.06
     Initialise
    0.06
    .kotlin
    0.06
    Activations Density 0.053%

    No Known Activations