© 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. 75281
    Prev
    Next
    INDEX
    Explanations

    similar modifiers and adjectives related to definitions and attributes

    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
    wg
    -0.07
    ampler
    -0.07
    ITLE
    -0.06
     Syntax
    -0.06
    eturn
    -0.06
    itage
    -0.06
    quet
    -0.06
    aida
    -0.06
    atsby
    -0.06
    _Impl
    -0.06
    POSITIVE LOGITS
     term
    0.11
     technique
    0.09
    ä¸Ģç§į
    0.09
    term
    0.08
    -term
    0.07
     Term
    0.07
    Term
    0.07
     phenomenon
    0.07
     tér
    0.07
     Technique
    0.06
    Activations Density 0.027%

    No Known Activations