© 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. 39576
    Prev
    Next
    INDEX
    Explanations

    references to honor and associated titles or distinctions

    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
     Vinci
    -0.07
    gere
    -0.07
    ãĥĭãĥĥãĤ¯
    -0.07
    ucer
    -0.07
    urge
    -0.07
    sis
    -0.07
    sWith
    -0.07
    ye
    -0.07
    _hdl
    -0.07
    ÙĬ
    -0.07
    POSITIVE LOGITS
    ably
    0.15
    ific
    0.12
    able
    0.09
    fast
    0.08
    atus
    0.08
    full
    0.08
    iginal
    0.07
    ABLE
    0.07
    ously
    0.07
    arium
    0.07
    Activations Density 0.014%

    No Known Activations