© 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
    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. 109892
    Prev
    Next
    INDEX
    Explanations

    problem solving methods

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “expressions.”

    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
    斷
    -0.07
    断
    -0.07
    ILED
    -0.06
    selector
    -0.06
    aining
    -0.06
    ,与
    -0.06
     countered
    -0.06
     WITH
    -0.06
     WHETHER
    -0.06
    pio
    -0.06
    POSITIVE LOGITS
    ###↵
    0.07
     deleteUser
    0.07
     investig
    0.07
     innovation
    0.06
    /Input
    0.06
    ]=-
    0.06
     ''}↵
    0.06
     คน
    0.06
     adjustments
    0.06
    _desc
    0.06
    Activations Density 0.471%

    No Known Activations