© 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. 56510
    Prev
    Next
    INDEX
    Explanations

    references to technical processes and professional evaluations

    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
    égor
    -0.08
    Ùıس
    -0.07
    witter
    -0.07
    ШÐIJ
    -0.07
    atron
    -0.07
     UIResponder
    -0.07
    eus
    -0.07
     noci
    -0.07
    ÑĢаÑĩ
    -0.07
    omik
    -0.07
    POSITIVE LOGITS
    ofil
    0.07
    msp
    0.06
     Mess
    0.06
    SEQUENTIAL
    0.06
    stral
    0.05
    ĻĤ
    0.05
    ÐĤ
    0.05
    pls
    0.05
    less
    0.05
    ishi
    0.05
    Activations Density 0.625%

    No Known Activations