© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128650
    Prev
    Next
    INDEX
    Explanations

    that was

    np_max-act · gemini-2.0-flash

    The neuron detects formal “lack‐of‐evidence” phrasing—especially the word “indicate” and its immediate follow-on (“that ever had a religious function”) signifying no proof.

    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
    Ra
    -0.06
    (step
    -0.06
     Zy
    -0.06
    Planning
    -0.06
    Hal
    -0.06
    holding
    -0.05
     Ulus
    -0.05
     setUser
    -0.05
    -0.05
    Birth
    -0.05
    POSITIVE LOGITS
     tmpl
    0.07
    _shared
    0.07
    stash
    0.07
     ticking
    0.07
    ioni
    0.07
     dapat
    0.07
     gutter
    0.06
    _POOL
    0.06
    +i
    0.06
     transcripts
    0.06
    Activations Density 0.033%

    No Known Activations