© 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. 92049
    Prev
    Next
    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    The neuron activates on conditional qualifiers and numeric thresholds (e.g. “if applicable,” “less than six,” “in number”), i.e. phrases that specify when something applies or set quantitative limits.

    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
     blood
    -0.07
    %%*/
    -0.07
    ROID
    -0.07
    需要
    -0.07
     animator
    -0.06
    skyt
    -0.06
    .qml
    -0.06
    Ν
    -0.06
    альным
    -0.06
     كر
    -0.06
    POSITIVE LOGITS
     Wid
    0.06
     commerc
    0.06
    -var
    0.06
     Edu
    0.06
    /docker
    0.06
     hvis
    0.06
    빈
    0.05
     commercially
    0.05
    े।↵
    0.05
     Milano
    0.05
    Activations Density 0.008%

    No Known Activations