© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104400
    Prev
    Next
    INDEX
    Explanations

    concepts related to timelessness and eternal value

    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
    asso
    -0.07
    apat
    -0.06
    ils
    -0.06
    asp
    -0.06
    eos
    -0.06
    yles
    -0.06
     Wol
    -0.06
     Patron
    -0.06
    ye
    -0.06
     cab
    -0.06
    POSITIVE LOGITS
    ingly
    0.08
    -looking
    0.08
    rovers
    0.07
    ãģªãģĮ
    0.07
    oti
    0.07
    ently
    0.07
     semp
    0.07
    rection
    0.07
    fect
    0.07
    -old
    0.07
    Activations Density 0.004%

    No Known Activations