© 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 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. 40484
    Prev
    Next
    INDEX
    Explanations

    references to notable achievements and recognition

    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
    imbus
    -0.06
    ноÑĩ
    -0.06
    ãĤ±ãĥĥãĥĪ
    -0.06
    á»IJ
    -0.06
    _trampoline
    -0.06
    cej
    -0.06
    .community
    -0.06
    810
    -0.06
     зад
    -0.06
    δο
    -0.06
    POSITIVE LOGITS
     wax
    0.07
    _clone
    0.07
     Imm
    0.07
     attraction
    0.06
     Batter
    0.06
    clone
    0.06
    (clone
    0.06
    elve
    0.06
     queue
    0.06
    .Virtual
    0.06
    Activations Density 0.001%

    No Known Activations