© 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. 30443
    Prev
    Next
    INDEX
    Explanations

    Code or configuration files

    np_max-act · gemini-2.0-flash

    The neuron activates on documentation-style phrases that define a command’s usage and behavior.

    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
    /script
    -0.08
     आद
    -0.07
     đào
    -0.07
    .mid
    -0.06
    締
    -0.06
     &&
    -0.06
     machinery
    -0.06
     mixer
    -0.06
     修改
    -0.06
    주시
    -0.06
    POSITIVE LOGITS
     setzen
    0.07
    .Alignment
    0.07
    ickým
    0.06
    iquer
    0.06
    .entities
    0.06
     Venus
    0.06
     afect
    0.06
     resultado
    0.06
     rum
    0.06
     Vel
    0.06
    Activations Density 0.085%

    No Known Activations