© 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. 127689
    Prev
    Next
    INDEX
    Explanations

    various forms and attributes of representations in a formal context

    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
    Ñıж
    -0.08
    esin
    -0.06
    ohana
    -0.06
    ATAB
    -0.06
     euth
    -0.06
    _LOC
    -0.06
    lava
    -0.06
    ılı
    -0.06
    wa
    -0.06
    sty
    -0.06
    POSITIVE LOGITS
     thereof
    0.07
     representation
    0.07
    hift
    0.07
    Hack
    0.06
     representations
    0.06
     of
    0.06
    orial
    0.06
    pager
    0.06
    _INITIALIZER
    0.06
    ronics
    0.06
    Activations Density 0.043%

    No Known Activations