© 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. 68797
    Prev
    Next
    INDEX
    Explanations

    muscle tissue research

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of quantitative tissue‐ or organ‐measurement terms (morphological and structural metrics).

    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
    icos
    -0.07
    по
    -0.07
    eling
    -0.06
     cursos
    -0.06
    ically
    -0.06
    award
    -0.06
     collusion
    -0.06
    enos
    -0.06
    -menu
    -0.06
     varsa
    -0.06
    POSITIVE LOGITS
     JOHN
    0.07
    @FindBy
    0.07
    menuItem
    0.06
    γό
    0.06
    Ｒ
    0.06
    ]]>
    0.06
    롤
    0.06
     Clarkson
    0.06
     reputed
    0.06
    ]='
    0.06
    Activations Density 0.019%

    No Known Activations