© 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. 125144
    Prev
    Next
    INDEX
    Explanations

    NOT

    np_max-act · gemini-2.0-flash

    The neuron fires on the “[DO NOT PUBLISH]” non-publication disclaimer in appellate court opinions.

    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
     potrze
    -0.06
    tte
    -0.06
    -Muslim
    -0.06
    ASURE
    -0.06
     στρα
    -0.06
    odash
    -0.06
     rf
    -0.06
    Fully
    -0.06
    avorites
    -0.06
    ाजस
    -0.06
    POSITIVE LOGITS
    	name
    0.07
    .DOWN
    0.06
     Emb
    0.06
     гум
    0.06
    langle
    0.06
     Nations
    0.06
     xPos
    0.06
     vul
    0.06
     cancelled
    0.06
    форма
    0.06
    Activations Density 0.006%

    No Known Activations