© 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. 15-RESID-POST-AA
    11. 89501
    Prev
    Next
    INDEX
    Explanations

    code parsing

    np_max-act · gemini-2.0-flash

    the neuron detects parser/test-run output lines that report parsing results and metadata (summary lines describing how the input was parsed).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кол
    -0.08
    ト
    -0.07
     Simmons
    -0.07
     regimen
    -0.06
    DataTask
    -0.06
    かわ
    -0.06
    (variable
    -0.06
    _STORAGE
    -0.06
    _atts
    -0.06
    Scene
    -0.06
    POSITIVE LOGITS
     archived
    0.06
     sufficiently
    0.06
    	sl
    0.06
     Calcium
    0.06
     resemblance
    0.06
     residue
    0.06
    annotation
    0.06
     vent
    0.05
    ])**
    0.05
     knot
    0.05
    Activations Density 0.000%

    No Known Activations