© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89095
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting indicators

    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
    ÙĪØ«
    -0.07
     Substance
    -0.06
     Åŀah
    -0.06
    á»·
    -0.06
    çIJĥ
    -0.06
    Ư
    -0.06
    ¶Į
    -0.06
    .'<
    -0.06
     Vig
    -0.06
     setHidden
    -0.06
    POSITIVE LOGITS
    renc
    0.06
     Emp
    0.06
    uled
    0.06
    ildi
    0.06
    utow
    0.06
    AGAIN
    0.06
    icina
    0.06
    unte
    0.06
    agnost
    0.06
     Independence
    0.06
    Activations Density 0.000%

    No Known Activations