© 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. 5591
    Prev
    Next
    INDEX
    Explanations

    phrases related to intention or purpose

    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
    aire
    -0.09
    naire
    -0.09
    ization
    -0.08
    ity
    -0.08
    izable
    -0.08
    yers
    -0.08
    eres
    -0.08
    isable
    -0.08
    ised
    -0.07
    thon
    -0.07
    POSITIVE LOGITS
    ures
    0.08
    ient
    0.08
    ually
    0.08
    ory
    0.08
    ual
    0.08
    fulness
    0.08
    ration
    0.08
    lessly
    0.07
    iful
    0.07
    ions
    0.07
    Activations Density 0.004%

    No Known Activations