© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29869
    Prev
    Next
    INDEX
    Explanations

    names of places or institutions

    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
    ois
    -0.07
    ãĥ¼ãĥĨãĤ£
    -0.06
    req
    -0.06
    _tE
    -0.06
    è·
    -0.06
    abr
    -0.06
    çĴ
    -0.06
     MainAxisAlignment
    -0.06
    bei
    -0.06
    orrow
    -0.06
    POSITIVE LOGITS
     Institute
    0.07
    lessly
    0.07
    undos
    0.07
    вÑĸлÑĮ
    0.06
     rep
    0.06
     Kin
    0.06
     Bast
    0.06
    ensity
    0.06
    dum
    0.06
    ripper
    0.06
    Activations Density 0.097%

    No Known Activations