© 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. 60912
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating time or frequency references

    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
    .accounts
    -0.08
    گراÙĨ
    -0.08
    vard
    -0.08
    .nlm
    -0.08
    ogie
    -0.07
    èm
    -0.07
    alta
    -0.07
    omit
    -0.07
     Handy
    -0.07
    essler
    -0.07
    POSITIVE LOGITS
     whose
    0.08
    arrison
    0.06
    cept
    0.06
     worth
    0.06
     exclusively
    0.06
    EEDED
    0.06
    esen
    0.06
    ing
    0.06
    ayed
    0.05
    whose
    0.05
    Activations Density 0.039%

    No Known Activations