© 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. 17-LLAMASCOPE-RES-131K
    11. 88152
    Prev
    Next
    INDEX
    Explanations

    time stamps or temporal 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
     cháy
    -0.07
    Subsystem
    -0.06
    æ¢
    -0.06
    ieu
    -0.06
    Parameter
    -0.06
    APA
    -0.06
    orum
    -0.06
    åİŁæľ¬
    -0.06
    Ñĥда
    -0.06
    edback
    -0.06
    POSITIVE LOGITS
     Reply
    0.07
    rane
    0.07
    ehler
    0.06
    omal
    0.06
    bens
    0.06
    eniz
    0.06
    amet
    0.06
    ENCIL
    0.06
    581
    0.06
     reply
    0.06
    Activations Density 0.007%

    No Known Activations