© 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. 75328
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and elements

    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
    raki
    -0.06
    emmel
    -0.06
    anvas
    -0.06
    onical
    -0.06
    lem
    -0.06
    olang
    -0.06
    ño
    -0.06
     grö
    -0.06
    gov
    -0.06
    à¹Ģลย
    -0.06
    POSITIVE LOGITS
     "&#
    0.07
     <<-
    0.06
    hashCode
    0.06
    ابÙĩ
    0.06
    /includes
    0.06
    QUEST
    0.06
     darauf
    0.06
    (?:
    0.06
    -addons
    0.06
    ãĥ³ãĥĩãĤ£
    0.06
    Activations Density 0.008%

    No Known Activations