© 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. 9-LLAMASCOPE-RES-131K
    11. 97680
    Prev
    Next
    INDEX
    Explanations

    team names and sporting events

    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
    zb
    -0.07
    assist
    -0.07
    оди
    -0.07
    çĸ
    -0.06
    ANGE
    -0.06
    wich
    -0.06
    elin
    -0.06
    èm
    -0.06
    Ñ
    -0.06
    983
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.07
    /lg
    0.07
    AtPath
    0.07
     Maul
    0.07
    avour
    0.06
     Boyd
    0.06
    MOVED
    0.06
    ãĥ¼ãĥł
    0.06
    _frontend
    0.06
    yll
    0.06
    Activations Density 0.033%

    No Known Activations