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. 9-LLAMASCOPE-RES-131K
    6. 95963
    Prev
    Next
    INDEX
    Explanations

    references to scalability and modularity in 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
    ISIBLE
    -0.07
    contest
    -0.07
    arks
    -0.07
     contest
    -0.06
    phil
    -0.06
     Contest
    -0.06
     Nack
    -0.06
    tec
    -0.06
    INET
    -0.06
    KNOWN
    -0.06
    POSITIVE LOGITS
    iping
    0.07
     Gon
    0.06
    ooter
    0.06
    ording
    0.06
    /vue
    0.06
    éĢĨ
    0.06
    رÙĬÙĥ
    0.06
    agas
    0.06
    ellas
    0.06
    yte
    0.05
    Activations Density 0.015%

    No Known Activations