© 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. 107814
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connective phrases indicating addition or similarity

    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
    302
    -0.07
     же
    -0.06
    870
    -0.06
    illions
    -0.06
    /lists
    -0.06
    éĤ£ä¹Ī
    -0.06
     various
    -0.06
    ALL
    -0.06
    Äĥng
    -0.06
    st
    -0.06
    POSITIVE LOGITS
    feit
    0.07
    orent
    0.07
    ÑĢÑĸÑĩ
    0.07
    iasi
    0.07
    άÏĤ
    0.07
    endir
    0.06
    tractive
    0.06
    phalt
    0.06
    grass
    0.06
     approach
    0.06
    Activations Density 0.042%

    No Known Activations