© 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. 92123
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on string literals representing relative file paths (i.e. paths beginning with “./”).

    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
     Whoever
    -0.07
    .buf
    -0.07
    <'
    -0.06
     '{}
    -0.06
     Wilson
    -0.06
    >").
    -0.06
     Year
    -0.06
     "***
    -0.06
    _BEFORE
    -0.06
    _texts
    -0.06
    POSITIVE LOGITS
     semaphore
    0.07
    osi
    0.06
     rdr
    0.06
    conference
    0.06
    ughter
    0.06
    constant
    0.06
    survey
    0.06
     ambit
    0.05
     Tv
    0.05
    asive
    0.05
    Activations Density 0.056%

    No Known Activations