© 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. 126997
    Prev
    Next
    INDEX
    Explanations

    references to samples or tests related to data and analysis

    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
    nod
    -0.06
    )↵↵↵↵↵↵↵↵
    -0.06
    lam
    -0.05
    izi
    -0.05
    ifen
    -0.05
    owers
    -0.05
    uto
    -0.05
    aida
    -0.05
    elsen
    -0.05
     Aviv
    -0.05
    POSITIVE LOGITS
    /sample
    0.10
    /template
    0.07
    IMENT
    0.07
    /example
    0.07
    asti
    0.07
    ssp
    0.07
    éric
    0.07
    #
    0.07
    bilt
    0.07
     biod
    0.07
    Activations Density 0.011%

    No Known Activations