© 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. 92005
    Prev
    Next
    INDEX
    Explanations

    finalization

    np_max-act · gemini-2.0-flash

    The neuron fires on words and numbers that signal a deal’s closing or completion timing (e.g. “close,” “completed,” “finalized,” and related dates/times).

    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
    Hel
    -0.07
    Compiler
    -0.07
    Bounds
    -0.06
     proxy
    -0.06
     rdf
    -0.06
    /master
    -0.06
    ScrollIndicator
    -0.06
     antigen
    -0.06
     Tracking
    -0.06
    Θ
    -0.06
    POSITIVE LOGITS
    BOOLE
    0.06
     fecha
    0.06
     nouvelles
    0.06
     deprived
    0.06
     Paula
    0.06
     revive
    0.06
    ，並
    0.06
     Vel
    0.05
     secrecy
    0.05
     информа
    0.05
    Activations Density 0.014%

    No Known Activations