© 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. 56435
    Prev
    Next
    INDEX
    Explanations

    references to "moss" and its related terms in various contexts

    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
    hir
    -0.07
    oop
    -0.07
    hon
    -0.07
    erna
    -0.07
    hs
    -0.07
    easy
    -0.07
    ection
    -0.07
    ulers
    -0.07
    hdr
    -0.07
    tabs
    -0.07
    POSITIVE LOGITS
    ed
    0.10
    es
    0.08
    iness
    0.08
    y
    0.08
    kop
    0.08
    LEC
    0.07
    eday
    0.07
    s
    0.07
    ses
    0.07
    berg
    0.07
    Activations Density 0.004%

    No Known Activations