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

    Neuronpedia

    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. 128410
    Prev
    Next
    INDEX
    Explanations

    action verbs related to improvement and achievement

    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
    θÎŃ
    -0.07
    permit
    -0.07
    _MET
    -0.07
    коз
    -0.07
    AWN
    -0.07
    uzu
    -0.07
     topLevel
    -0.06
    iox
    -0.06
    ahat
    -0.06
    isy
    -0.06
    POSITIVE LOGITS
    ings
    0.11
    it
    0.07
    auf
    0.07
    able
    0.07
    gings
    0.07
    its
    0.06
    ingly
    0.06
    elli
    0.06
    ingo
    0.06
    ichtet
    0.06
    Activations Density 0.070%

    No Known Activations