© 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. 40727
    Prev
    Next
    INDEX
    Explanations

    terms related to specific hobbies, interests, or fandoms

    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
    ngo
    -0.08
    illow
    -0.08
    iverz
    -0.08
    idth
    -0.07
    erli
    -0.07
    ções
    -0.07
    ixe
    -0.07
    avis
    -0.07
    _DEFINE
    -0.07
    stras
    -0.07
    POSITIVE LOGITS
     who
    0.08
    IDGE
    0.07
     بÙĪدÙĨ
    0.07
    747
    0.07
    ê·¹
    0.06
    614
    0.06
    -light
    0.06
    ih
    0.06
    اÙĨÙĩ
    0.06
    who
    0.06
    Activations Density 0.023%

    No Known Activations