Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5193
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure in code snippets

    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
    âĢĮâĢĮ
    -0.07
    acob
    -0.07
    icerca
    -0.06
    aphore
    -0.06
    è¨
    -0.06
    ictures
    -0.06
    ASF
    -0.06
    poly
    -0.06
    liche
    -0.06
    ulp
    -0.06
    POSITIVE LOGITS
    igans
    0.07
    969
    0.07
    ãĤ¸ãĤª
    0.07
     âĨIJ
    0.06
    ênh
    0.06
    ìĿ´ìĹIJ
    0.06
    Ĩ
    0.06
     Span
    0.06
    span
    0.06
     span
    0.06
    Activations Density 0.040%

    No Known Activations