© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55833
    Prev
    Next
    INDEX
    Explanations

    memory leaks

    np_max-act · gemini-2.0-flash

    The neuron flags programming identifiers and technical code tokens (e.g. class, function, and object names).

    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
    opers
    -0.07
    vič
    -0.07
     wanna
    -0.06
    番
    -0.06
    공
    -0.06
     때
    -0.06
    ax
    -0.06
    ())↵
    -0.06
    goals
    -0.06
     prefs
    -0.06
    POSITIVE LOGITS
    .uint
    0.07
     Spy
    0.07
     invent
    0.06
     shirt
    0.06
    _WAIT
    0.06
     Laundry
    0.06
     ht
    0.06
     Scre
    0.06
    욕
    0.06
     imagin
    0.06
    Activations Density 0.027%

    No Known Activations