© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30503
    Prev
    Next
    INDEX
    Explanations

    commercialization

    np_max-act · gemini-2.0-flash

    The neuron fires on terms and phrases describing commercial or industrial application and market‐oriented development of research and technology.

    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
     purported
    -0.07
    .longitude
    -0.07
    outine
    -0.07
    mask
    -0.07
     Discord
    -0.06
    pat
    -0.06
    encrypt
    -0.06
    ї
    -0.06
    WithValue
    -0.06
    --+
    -0.06
    POSITIVE LOGITS
    +B
    0.06
    _Struct
    0.06
    onomic
    0.06
    穴
    0.06
    (vertices
    0.06
    elas
    0.06
     appeals
    0.06
    (fc
    0.05
    _fitness
    0.05
     strap
    0.05
    Activations Density 0.009%

    No Known Activations