© 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. 118597
    Prev
    Next
    INDEX
    Explanations

    features related to translation technology

    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
    odos
    -0.07
    enburg
    -0.07
     Hod
    -0.07
    ply
    -0.07
    å¸ĥ
    -0.07
    inecraft
    -0.06
    abez
    -0.06
     cron
    -0.06
    sale
    -0.06
    het
    -0.06
    POSITIVE LOGITS
     speech
    0.07
     Romance
    0.07
     Transformer
    0.07
     dá»ĭch
    0.07
    Chunks
    0.06
     ë²Ī
    0.06
     automát
    0.06
    .Trans
    0.06
    /input
    0.06
     input
    0.06
    Activations Density 0.011%

    No Known Activations