Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55002
    Prev
    Next
    INDEX
    Explanations

    parts replacement

    np_max-act · gemini-2.0-flash

    This neuron detects language signaling the need to replace or replaceable parts.

    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
     outings
    -0.06
    Sequence
    -0.06
     RUNNING
    -0.06
     Sym
    -0.06
    	cnt
    -0.06
    腰
    -0.06
     membership
    -0.05
    ()<<"
    -0.05
    Hmm
    -0.05
    scopy
    -0.05
    POSITIVE LOGITS
    ุบาล
    0.08
     pojist
    0.08
     gusto
    0.07
    Install
    0.07
     belirli
    0.07
    ниць
    0.07
     Elemental
    0.07
    adratic
    0.07
     файла
    0.06
     Серед
    0.06
    Activations Density 0.023%

    No Known Activations