© 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. 85822
    Prev
    Next
    INDEX
    Explanations

    Abbreviations/Acronyms

    np_max-act · gemini-2.0-flash

    The neuron fires on uppercase acronyms and program names (e.g. “E-rate,” “HACCP,” “EPODE,” “TRIZ,” etc.).

    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
    Counter
    -0.07
    sessions
    -0.06
     deadlines
    -0.06
     správ
    -0.06
     perpetrators
    -0.06
     dismissal
    -0.06
     temps
    -0.06
    guild
    -0.06
    /stdc
    -0.06
     duration
    -0.06
    POSITIVE LOGITS
     tagName
    0.07
     BOOL
    0.06
    нак
    0.06
     achieved
    0.06
    าม
    0.06
     '..
    0.06
    JOB
    0.06
    aniel
    0.06
     OCI
    0.06
     ؛
    0.06
    Activations Density 0.024%

    No Known Activations