© 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. 42641
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of “pdb” (and other similar uppercase database/module‐ID tokens), i.e. it detects references to PDB accession codes in code or URLs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    codes related to scientific and technical documentation.

    oai_token-act-pair · gpt-4o-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
     번
    -0.06
     คล
    -0.06
    _LAT
    -0.06
    lemetry
    -0.06
     Мик
    -0.06
     spectral
    -0.06
     комплек
    -0.06
     trade
    -0.06
    諸
    -0.06
     denne
    -0.06
    POSITIVE LOGITS
    Arthur
    0.07
    GenericType
    0.07
    >'.$
    0.07
    ?,?,
    0.07
    ___
    0.07
    Yet
    0.06
    _SCHEMA
    0.06
    PDOException
    0.06
    ?,?,?,?,
    0.06
     ری
    0.06
    Activations Density 0.000%

    No Known Activations