© 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. 110197
    Prev
    Next
    INDEX
    Explanations

    detailed instructions

    np_max-act · gemini-2.0-flash

    This neuron detects the specific phrase “in order 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
    74
    -0.08
    يب
    -0.07
    OVER
    -0.07
     Reed
    -0.06
     sys
    -0.06
    Titulo
    -0.06
     diverted
    -0.06
    LANG
    -0.06
     manipulated
    -0.06
    女性
    -0.06
    POSITIVE LOGITS
    \Extension
    0.07
     характ
    0.06
     maxlength
    0.06
    .states
    0.06
     undisclosed
    0.06
    (Language
    0.06
    はず
    0.06
     Friend
    0.06
    .Use
    0.06
    .Des
    0.06
    Activations Density 0.046%

    No Known Activations