© 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. 14794
    Prev
    Next
    INDEX
    Explanations

    references to collaboration or partnerships in different 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
     CONSEQUENTIAL
    -0.07
    goto
    -0.07
    ennen
    -0.07
    uetype
    -0.07
    itage
    -0.07
    isbury
    -0.07
    plor
    -0.07
    *>(&
    -0.07
    verture
    -0.07
    oke
    -0.07
    POSITIVE LOGITS
     aim
    0.09
     purpose
    0.07
     objective
    0.07
     goal
    0.07
    ym
    0.06
     intention
    0.06
     Seal
    0.06
     acronym
    0.06
    ureau
    0.06
    unik
    0.06
    Activations Density 0.019%

    No Known Activations