© 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 EvalsExportsinterp-engineNEWAPI 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. 42246
    Prev
    Next
    INDEX
    Explanations

    phrases indicating offerings or dedications to individuals or groups

    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
     æ¬
    -0.06
     Royale
    -0.06
    awy
    -0.06
    asion
    -0.06
    ahren
    -0.06
     å·Ŀ
    -0.06
     Chew
    -0.06
    sel
    -0.06
    ominator
    -0.06
    indr
    -0.06
    POSITIVE LOGITS
    berger
    0.07
    lags
    0.07
    ORAGE
    0.07
    —for
    0.07
     sake
    0.06
    UTERS
    0.06
    ró
    0.06
    lag
    0.06
    (for
    0.06
    kaar
    0.06
    Activations Density 0.016%

    No Known Activations