© 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. 105883
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements or dimensions

    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
    anger
    -0.06
     lia
    -0.06
    abis
    -0.06
    aja
    -0.06
    ays
    -0.05
    dik
    -0.05
     Bam
    -0.05
    egr
    -0.05
     inline
    -0.05
    one
    -0.05
    POSITIVE LOGITS
    士
    0.07
    olson
    0.07
    ç¡
    0.07
    ÑĤÑİ
    0.07
    ÏĦοÏħÏĤ
    0.07
    олÑĸ
    0.07
    ffe
    0.07
     Demir
    0.07
    .mit
    0.07
    -scrollbar
    0.07
    Activations Density 0.019%

    No Known Activations