© 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. 13010
    Prev
    Next
    INDEX
    Explanations

    written content

    np_max-act · gemini-2.0-flash

    The neuron fires on structural or instructional terms in writing templates (e.g. “content,” “pillar,” “importance”), flagging words tied to the document’s outline or formatting guidelines.

    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
    .SECONDS
    -0.06
    Legend
    -0.06
    /cupertino
    -0.06
    λει
    -0.06
     名無し
    -0.06
     마음
    -0.06
    UBY
    -0.06
     IndexError
    -0.06
    سوب
    -0.06
     Guy
    -0.06
    POSITIVE LOGITS
    ��
    0.08
     shim
    0.07
     Banking
    0.06
    hill
    0.06
     марш
    0.06
     synt
    0.06
    ',↵↵
    0.06
     Fun
    0.06
     Cycling
    0.06
    "/></
    0.06
    Activations Density 0.000%

    No Known Activations