© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61032
    Prev
    Next
    INDEX
    Explanations

    terms related to inclusion and inclusivity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fw
    -0.08
    ickle
    -0.08
    trak
    -0.07
    enia
    -0.07
    elin
    -0.07
    esis
    -0.07
    oor
    -0.07
    алеж
    -0.07
    _DIRECTION
    -0.07
    lev
    -0.07
    POSITIVE LOGITS
    iveness
    0.09
    ness
    0.07
    NESS
    0.07
    /ex
    0.07
    ary
    0.06
     Ada
    0.06
    istan
    0.06
    .Cryptography
    0.06
     ter
    0.06
    ively
    0.06
    Activations Density 0.007%

    No Known Activations