© 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. 126713
    Prev
    Next
    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash

    This neuron detects Go function declarations or method signatures that include an “error” return type.

    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
    .deepcopy
    -0.08
     dispatch
    -0.07
    Hat
    -0.06
    AMESPACE
    -0.06
     qualifier
    -0.06
    Checksum
    -0.06
    .PUT
    -0.06
     uploading
    -0.06
     PYTHON
    -0.06
    ском
    -0.06
    POSITIVE LOGITS
     supervise
    0.08
    Stephen
    0.07
     Stephen
    0.07
     ero
    0.06
    _probe
    0.06
     Flores
    0.06
     adjustable
    0.06
    Well
    0.06
    oa
    0.06
     thai
    0.06
    Activations Density 0.002%

    No Known Activations