© 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. 17-LLAMASCOPE-RES-131K
    6. 40076
    Prev
    Next
    INDEX
    Explanations

    time-related indicators and their context

    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
    etten
    -0.08
    ajas
    -0.07
    ette
    -0.07
    yms
    -0.07
    ropp
    -0.07
     Duty
    -0.07
    hua
    -0.07
    itura
    -0.07
    rase
    -0.07
    ertas
    -0.06
    POSITIVE LOGITS
    351
    0.06
    396
    0.06
    ger
    0.06
    angled
    0.06
    _NAMESPACE
    0.06
     everywhere
    0.06
    620
    0.06
    619
    0.05
    enu
    0.05
     Gle
    0.05
    Activations Density 0.000%

    No Known Activations