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. 5244
    Prev
    Next
    INDEX
    Explanations

    mentions of attachment and related concepts

    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
    -ÑĤо
    -0.09
    erer
    -0.08
    jvu
    -0.08
    οÏħÏĥ
    -0.07
    ãĥ³ãĥij
    -0.07
    jedn
    -0.07
    аÑĤо
    -0.07
    jte
    -0.07
    stown
    -0.07
    rie
    -0.07
    POSITIVE LOGITS
    ments
    0.11
    ement
    0.10
    ements
    0.09
    /embed
    0.08
    é
    0.08
    ment
    0.07
    ivity
    0.07
    able
    0.07
    ively
    0.07
    ities
    0.07
    Activations Density 0.009%

    No Known Activations