© 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. 15-LLAMASCOPE-RES-131K
    11. 87226
    Prev
    Next
    INDEX
    Explanations

    topics of interest or enthusiasm expressed by individuals

    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
    arily
    -0.07
    sey
    -0.07
    asu
    -0.07
    pri
    -0.07
    kara
    -0.06
    PLE
    -0.06
    155
    -0.06
    hem
    -0.06
    antor
    -0.06
    steen
    -0.06
    POSITIVE LOGITS
    -looking
    0.08
    ness
    0.08
    untu
    0.07
    ±Ð¾ÑĤ
    0.07
    Å¡em
    0.06
    NESS
    0.06
    ή
    0.06
    assin
    0.06
    ijkstra
    0.06
    ooting
    0.06
    Activations Density 0.010%

    No Known Activations