© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28777
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations related to organizations and entities

    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
    umbn
    -0.09
    RIPT
    -0.08
    TURE
    -0.07
    WEEN
    -0.07
    TION
    -0.07
    fol
    -0.07
    AZY
    -0.07
    TEGER
    -0.07
    EMENT
    -0.07
    coma
    -0.07
    POSITIVE LOGITS
    s
    0.13
    /OR
    0.10
    AM
    0.07
    ÄIJT
    0.07
    sie
    0.07
    sWith
    0.07
    rientation
    0.07
    efe
    0.07
    aaS
    0.07
    avor
    0.07
    Activations Density 0.033%

    No Known Activations