© 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. 4236
    Prev
    Next
    INDEX
    Explanations

    data-related terminology and specific details

    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
    ATAB
    -0.07
    uble
    -0.07
    gren
    -0.07
    anel
    -0.07
    oce
    -0.06
    atab
    -0.06
    abilit
    -0.06
    _WARN
    -0.06
    etic
    -0.06
    ãĥ¼ãĥ©
    -0.06
    POSITIVE LOGITS
     Briggs
    0.08
    lap
    0.07
    396
    0.07
     Braun
    0.07
    elor
    0.07
    aint
    0.07
    772
    0.06
    redo
    0.06
    ób
    0.06
    apyrus
    0.06
    Activations Density 0.002%

    No Known Activations