© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126651
    Prev
    Next
    INDEX
    Explanations

    patterns of time-related actions or sequences in narratives

    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
    iller
    -0.07
    ads
    -0.07
    wers
    -0.06
    less
    -0.06
    lil
    -0.06
    uth
    -0.06
    ditor
    -0.06
    ì¡´
    -0.06
    pras
    -0.06
    دÙĨ
    -0.06
    POSITIVE LOGITS
     Stap
    0.08
     Stout
    0.07
    èĵ
    0.07
    ัวร
    0.07
    mint
    0.07
    ERGE
    0.07
     Conj
    0.06
    neath
    0.06
    ently
    0.06
     stap
    0.06
    Activations Density 0.004%

    No Known Activations