© 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. 29474
    Prev
    Next
    INDEX
    Explanations

    references to holistic health and wellness practices

    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
    èĦĤ
    -0.07
    quina
    -0.06
    ÑĢоÑĩ
    -0.06
    lld
    -0.06
    bau
    -0.06
     aray
    -0.06
     Sous
    -0.06
    lap
    -0.06
    _DIP
    -0.06
    enek
    -0.06
    POSITIVE LOGITS
     nob
    0.07
     Nob
    0.07
    YRO
    0.06
    essler
    0.06
    ording
    0.06
    isoft
    0.06
    amt
    0.06
     nos
    0.06
    phin
    0.06
     allerg
    0.06
    Activations Density 0.004%

    No Known Activations