© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78844
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or intent

    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
    ycz
    -0.06
    ulo
    -0.06
    rieve
    -0.06
    air
    -0.06
    our
    -0.06
    lessly
    -0.06
    å»
    -0.06
    aurant
    -0.06
    .EntityManager
    -0.06
    ery
    -0.06
    POSITIVE LOGITS
     example
    0.14
     exemplo
    0.10
     ejemplo
    0.10
     instance
    0.10
    unately
    0.09
    example
    0.09
    EXAMPLE
    0.09
    ä¾ĭ
    0.09
    -example
    0.09
    _example
    0.08
    Activations Density 0.008%

    No Known Activations