© 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. 119458
    Prev
    Next
    INDEX
    Explanations

    structures or definitions related to programming or technical specifications

    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
    azzi
    -0.07
    morgan
    -0.07
    igner
    -0.07
    edii
    -0.07
    erner
    -0.07
    isay
    -0.07
    éĽĦ
    -0.07
    rahim
    -0.06
    adolu
    -0.06
    otton
    -0.06
    POSITIVE LOGITS
    uur
    0.07
     Madden
    0.07
    ForRow
    0.06
    ERE
    0.06
     Ere
    0.06
    U
    0.06
    uch
    0.06
     astronom
    0.06
     Freed
    0.06
     Rag
    0.06
    Activations Density 0.001%

    No Known Activations