© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57467
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron specifically lights up on the words of the instruction phrase “filling in the,” i.e. it detects that exact sequence of function words.

    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
    scp
    -0.07
     plurality
    -0.07
    模型
    -0.07
     Takım
    -0.07
     |-
    -0.07
     escalate
    -0.07
    ворю
    -0.06
     Rusya
    -0.06
    平方公里
    -0.06
    elocity
    -0.06
    POSITIVE LOGITS
    ,c
    0.06
     inhib
    0.06
     нас
    0.06
    .addAttribute
    0.06
     inn
    0.06
    :Any
    0.06
     unins
    0.06
    Ln
    0.06
     cracks
    0.06
     Hin
    0.06
    Activations Density 0.005%

    No Known Activations