© 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. 84517
    Prev
    Next
    INDEX
    Explanations

    general concepts or ideas that are deemed significant

    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
    tk
    -0.07
    adin
    -0.07
    igli
    -0.07
    .ObjectId
    -0.07
    onga
    -0.06
    èı¯
    -0.06
    ypy
    -0.06
    ords
    -0.06
    ipur
    -0.06
     Duty
    -0.06
    POSITIVE LOGITS
     happening
    0.07
    .bb
    0.06
     done
    0.06
    umann
    0.06
    angstrom
    0.06
    aminer
    0.06
    	done
    0.06
    iator
    0.06
    ousse
    0.06
     Sticky
    0.06
    Activations Density 0.007%

    No Known Activations