© 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. 89183
    Prev
    Next
    INDEX
    Explanations

    terms related to enrollment, requirements, and academic processes

    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
    esub
    -0.07
    indle
    -0.07
    xad
    -0.06
    Lit
    -0.06
    rob
    -0.06
    olis
    -0.06
     ald
    -0.06
    zap
    -0.06
    nbr
    -0.06
    icial
    -0.06
    POSITIVE LOGITS
     closest
    0.07
     nearest
    0.07
    ience
    0.06
    PLEX
    0.06
     ONLY
    0.06
    Ä
    0.06
     instead
    0.06
    closest
    0.06
    faith
    0.06
    ÅĽcie
    0.06
    Activations Density 0.015%

    No Known Activations