© 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. 125079
    Prev
    Next
    INDEX
    Explanations

    Instance

    np_max-act · gemini-2.0-flash

    This neuron lights up on fragments of file paths or URLs (i.e. tokens containing “/” or parts of directory/filename strings).

    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
    尾
    -0.07
     guerr
    -0.06
    Eq
    -0.06
    Sol
    -0.06
     crush
    -0.06
    _ACCEPT
    -0.06
     fora
    -0.06
     aspect
    -0.06
    Hooks
    -0.06
    _func
    -0.06
    POSITIVE LOGITS
    ZR
    0.07
     MU
    0.07
    ↵    ↵↵
    0.07
    OURCE
    0.06
    FINITE
    0.06
     없어
    0.06
     DESCRIPTION
    0.06
    codegen
    0.06
    .XtraEditors
    0.06
    )}↵↵
    0.06
    Activations Density 0.330%

    No Known Activations