© 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. 109451
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash

    This neuron fires on the “clean” command in shell scripts (i.e. lines invoking a cleanup step).

    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
    ětš
    -0.07
     alors
    -0.07
     War
    -0.06
     což
    -0.06
     GWei
    -0.06
    CLUS
    -0.06
     hashMap
    -0.06
     VW
    -0.06
    _IMPORTED
    -0.06
     Bilg
    -0.06
    POSITIVE LOGITS
    LINE
    0.07
    _PLAY
    0.07
     bans
    0.06
     Công
    0.06
    ै।
    0.06
    ))}↵
    0.06
    .Long
    0.06
    engeance
    0.06
    >')↵
    0.06
     hayvan
    0.06
    Activations Density 0.016%

    No Known Activations