© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92370
    Prev
    Next
    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “migrations,” i.e. it detects mentions of migration files or commands.

    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
     aliens
    -0.07
    Witness
    -0.07
    Bei
    -0.07
     Lud
    -0.07
     Depends
    -0.06
    tuk
    -0.06
    lesia
    -0.06
    цез
    -0.06
     Unter
    -0.06
     Manuals
    -0.06
    POSITIVE LOGITS
    郑
    0.06
     查
    0.06
     انگلیسی
    0.06
    Checking
    0.06
    .\
    0.06
    etí
    0.06
    *******/↵↵
    0.06
     discrimin
    0.06
    購
    0.06
    NSMutable
    0.06
    Activations Density 0.000%

    No Known Activations