© 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. 74837
    Prev
    Next
    INDEX
    Explanations

    review-related phrases and titles

    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
     oto
    -0.07
    @update
    -0.07
    èĻ
    -0.06
    prit
    -0.06
    esty
    -0.06
    вин
    -0.06
    ight
    -0.06
    owitz
    -0.06
    ãĥ¼ãĥĪ
    -0.06
    .lab
    -0.06
    POSITIVE LOGITS
    allee
    0.07
    ÑĢогÑĢа
    0.06
    reinterpret
    0.06
    ctxt
    0.06
     classNames
    0.06
    ankind
    0.06
    blers
    0.06
    ãĢİ
    0.06
     ‘
    0.06
    ehler
    0.06
    Activations Density 0.012%

    No Known Activations