© 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. 127030
    Prev
    Next
    INDEX
    Explanations

    time and date 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
    //{{
    -0.09
    oldur
    -0.08
    -strokes
    -0.07
    etik
    -0.07
    ãĥ¼ãĥ©
    -0.07
     strokes
    -0.07
    Äįer
    -0.07
    xor
    -0.07
    orsche
    -0.07
    esine
    -0.07
    POSITIVE LOGITS
     tum
    0.07
     èij
    0.06
     elabor
    0.06
    owitz
    0.06
    _heap
    0.06
    iller
    0.05
     hind
    0.05
    ulle
    0.05
    -Sep
    0.05
     pil
    0.05
    Activations Density 0.008%

    No Known Activations