© 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. 78364
    Prev
    Next
    INDEX
    Explanations

    occurrences of keywords or key phrases

    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
     Torres
    -0.06
     bound
    -0.06
    cco
    -0.06
    -Smith
    -0.06
     Lawn
    -0.06
    icer
    -0.05
     Relief
    -0.05
    ÑĤий
    -0.05
     spe
    -0.05
    aha
    -0.05
    POSITIVE LOGITS
    elow
    0.08
    aber
    0.07
    marsh
    0.07
    Tuple
    0.07
     engel
    0.07
    PathParam
    0.07
    ãĥ³ãĥĦ
    0.07
    нÑıÑĤ
    0.07
    ály
    0.07
    vern
    0.07
    Activations Density 0.001%

    No Known Activations