© 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. 755
    Prev
    Next
    INDEX
    Explanations

    hand

    np_max-act · gemini-2.0-flash

    The neuron responds to Italian anatomical terms—especially body parts mentioned in exercise instructions (e.g. mani, piedi, ginocchia, gambe).

    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
     Hud
    -0.07
    -reported
    -0.07
    _saved
    -0.07
     fab
    -0.07
     punk
    -0.07
    med
    -0.06
     sluggish
    -0.06
    mind
    -0.06
     down
    -0.06
    _listener
    -0.06
    POSITIVE LOGITS
    ATYPE
    0.07
     STD
    0.07
    .ToString
    0.06
     ऐस
    0.06
     Unable
    0.06
    一级
    0.06
     volatile
    0.06
     вклад
    0.06
     ا
    0.06
    -search
    0.06
    Activations Density 0.017%

    No Known Activations