© 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. 68875
    Prev
    Next
    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the compound name “curcumin” (i.e. the subword pieces cur-c-umin) in the text.

    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
    enarios
    -0.07
     داش
    -0.07
     empath
    -0.07
     EQUI
    -0.07
    SOR
    -0.06
    озмож
    -0.06
     Niagara
    -0.06
     Palmer
    -0.06
    _workers
    -0.06
    .decor
    -0.06
    POSITIVE LOGITS
     traceback
    0.07
    訴
    0.06
    裡
    0.06
    _processes
    0.06
    訓
    0.06
     Cp
    0.06
     pubb
    0.06
    xbd
    0.06
    (signature
    0.06
     inaccessible
    0.06
    Activations Density 0.000%

    No Known Activations