© 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. 6860
    Prev
    Next
    INDEX
    Explanations

    effort

    np_max-act · gemini-2.0-flash

    The neuron activates on words signaling an attempted action or purpose, especially occurrences of “effort” (e.g. in “in an effort to…”).

    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
    composed
    -0.07
    iseconds
    -0.07
     principles
    -0.07
    (""))↵
    -0.06
     vim
    -0.06
     fulfil
    -0.06
    時の
    -0.06
    fec
    -0.06
    地域
    -0.06
     своєї
    -0.06
    POSITIVE LOGITS
     hoping
    0.07
     Крас
    0.06
     rais
    0.06
    .SetActive
    0.06
    dns
    0.06
     HOWEVER
    0.06
    _shop
    0.06
     pick
    0.06
    radan
    0.06
    ًا
    0.06
    Activations Density 0.013%

    No Known Activations