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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 30263
    Prev
    Next
    INDEX
    Explanations

    specialization

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on domain-specialist adjectives (e.g. clinical, scientific, technical, academic).

    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
    Av
    -0.08
     Av
    -0.07
    다가
    -0.06
     下载
    -0.06
     ním
    -0.06
    dfs
    -0.06
    ichert
    -0.06
    >');↵
    -0.06
     vydání
    -0.06
    Rand
    -0.06
    POSITIVE LOGITS
     surrender
    0.07
    .DataContext
    0.07
     foam
    0.07
     produits
    0.06
    warnings
    0.06
     Doctrine
    0.06
     tolerate
    0.06
    Inside
    0.06
     getLocation
    0.06
     Safe
    0.06
    Activations Density 0.147%

    No Known Activations