© 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. 86428
    Prev
    Next
    INDEX
    Explanations

    concepts related to ease of understanding and accessibility

    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
    finally
    -0.07
    æīį
    -0.07
    wig
    -0.07
    akah
    -0.07
    illy
    -0.06
    ilton
    -0.06
     Uniform
    -0.06
    öl
    -0.06
    amina
    -0.06
    Uniform
    -0.06
    POSITIVE LOGITS
     unless
    0.10
    WithValue
    0.09
     вполне
    0.08
    unless
    0.08
     even
    0.08
     provided
    0.08
     Provided
    0.08
     if
    0.08
     Unless
    0.08
     PROVIDED
    0.07
    Activations Density 0.053%

    No Known Activations