© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68811
    Prev
    Next
    INDEX
    Explanations

    non-something

    np_max-act · gemini-2.0-flash

    The neuron detects words built on the “multi-” (or “non-multi-”) root—e.g. multiple, multiplex, non-multiple, 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
     beds
    -0.07
     preach
    -0.07
     nu
    -0.06
    аки
    -0.06
     rows
    -0.06
     escaped
    -0.06
     blot
    -0.06
     subsection
    -0.06
     raid
    -0.06
     buckets
    -0.06
    POSITIVE LOGITS
    exc
    0.07
     těž
    0.07
     Serbian
    0.07
    ého
    0.06
    .Enable
    0.06
    .invokeLater
    0.06
    _conf
    0.06
    Emp
    0.06
    ″E
    0.06
     getClient
    0.06
    Activations Density 0.064%

    No Known Activations