© 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. 6433
    Prev
    Next
    INDEX
    Explanations

    uncertainty and denial

    np_max-act · gemini-2.0-flash

    This neuron detects the cue “so it’s safe to assume…” (and similar phrasing) that introduces a rhetorical assumption or inference.

    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
    _short
    -0.07
     Cop
    -0.07
    archive
    -0.06
     archive
    -0.06
    ilo
    -0.06
    LogFile
    -0.06
     fever
    -0.06
     motivated
    -0.06
    ivy
    -0.06
     тих
    -0.06
    POSITIVE LOGITS
     PCA
    0.06
     -->
    0.06
     sanitize
    0.06
     retry
    0.06
     bot
    0.06
     deterior
    0.06
     […]↵↵
    0.06
    .IN
    0.06
     midd
    0.06
     rf
    0.05
    Activations Density 0.002%

    No Known Activations