© 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. 28945
    Prev
    Next
    INDEX
    Explanations

    references to personal assistance or support

    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
    acco
    -0.07
     Perf
    -0.06
    tery
    -0.06
     Kang
    -0.06
    Äįka
    -0.06
    yah
    -0.06
    unate
    -0.06
    net
    -0.06
    nett
    -0.06
    iler
    -0.06
    POSITIVE LOGITS
    /us
    0.10
     {{{
    0.07
    ÐŁÐļ
    0.07
    -même
    0.06
    aliz
    0.06
    ãĥĥãĥĪ
    0.06
    Úĺ
    0.06
    WithContext
    0.06
    ("(%
    0.06
    /tos
    0.06
    Activations Density 0.009%

    No Known Activations