© 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. 30223
    Prev
    Next
    INDEX
    Explanations

    man

    np_max-act · gemini-2.0-flash

    The neuron is triggered by text strings that form argument‐related error messages (e.g. “Missing required argument,” “Too many non‐option arguments,” “Argument requis manquant,” etc.).

    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
    klady
    -0.08
    .getPort
    -0.08
     yacht
    -0.07
    -band
    -0.06
    Markers
    -0.06
    ots
    -0.06
     Nir
    -0.06
    sea
    -0.06
    iative
    -0.06
     proposals
    -0.06
    POSITIVE LOGITS
     ｀
    0.07
     vou
    0.07
     escri
    0.06
     رف
    0.06
    ौकर
    0.06
    >Error
    0.06
     PyQt
    0.06
    ัตว
    0.06
     ActivityCompat
    0.06
    脱
    0.06
    Activations Density 0.175%

    No Known Activations