© 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. 58918
    Prev
    Next
    INDEX
    Explanations

    concepts related to hereditary traits and generational continuity

    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
    ãĥ¼ãĥij
    -0.07
    γκα
    -0.07
    walker
    -0.06
    ulp
    -0.06
    eshire
    -0.06
    _esc
    -0.06
    üz
    -0.06
    /min
    -0.06
     @}
    -0.06
     forcing
    -0.06
    POSITIVE LOGITS
     generations
    0.10
     generation
    0.09
     passed
    0.09
     passing
    0.09
     Passed
    0.08
    generation
    0.08
     Generation
    0.08
    ofs
    0.07
     Passing
    0.07
     Gener
    0.07
    Activations Density 0.010%

    No Known Activations