© 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. 78086
    Prev
    Next
    INDEX
    Explanations

    commas in various contexts, indicating pauses or separations in information

    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
    ucken
    -0.08
    reesome
    -0.07
    ãģªãģı
    -0.06
    umlu
    -0.06
    ives
    -0.06
     League
    -0.06
    632
    -0.06
    als
    -0.06
     Ring
    -0.06
     meiden
    -0.06
    POSITIVE LOGITS
    Inset
    0.07
    aday
    0.07
     bid
    0.07
    _hooks
    0.06
    acon
    0.06
    onas
    0.06
    eon
    0.06
    ifar
    0.06
    _Str
    0.06
    atrix
    0.06
    Activations Density 0.023%

    No Known Activations