© 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. 81684
    Prev
    Next
    INDEX
    Explanations

    mention of researchers and their affiliations or contributions

    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
    ادا
    -0.07
    ossa
    -0.07
    uala
    -0.07
    çĺ
    -0.07
    istrovstvÃŃ
    -0.07
    emez
    -0.07
    ùi
    -0.06
    ULA
    -0.06
    ì²´
    -0.06
    LATED
    -0.06
    POSITIVE LOGITS
     team
    0.10
     teams
    0.09
    team
    0.08
     researchers
    0.08
     professor
    0.08
    -team
    0.07
     colleagues
    0.07
     et
    0.07
    research
    0.07
    teams
    0.07
    Activations Density 0.017%

    No Known Activations