© 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. 57635
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of enzymes and their properties

    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
    dna
    -0.07
    _ASCII
    -0.07
    лоп
    -0.07
    apiro
    -0.06
     visibility
    -0.06
    avez
    -0.06
    ifty
    -0.06
    (visible
    -0.06
    ologi
    -0.06
    hardt
    -0.06
    POSITIVE LOGITS
     Structure
    0.07
    æ£ĭçīĮ
    0.07
     properties
    0.06
    étique
    0.06
     structure
    0.06
    λε
    0.06
    ustral
    0.06
    andidate
    0.06
    Structure
    0.06
    Łèĥ½
    0.06
    Activations Density 0.012%

    No Known Activations