© 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. 17-LLAMASCOPE-RES-131K
    11. 119770
    Prev
    Next
    INDEX
    Explanations

    references to complexity and complex systems

    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
    è¾°
    -0.08
    lap
    -0.07
    resi
    -0.07
    ubic
    -0.07
    bage
    -0.07
    _nsec
    -0.07
    etry
    -0.06
    iler
    -0.06
    aping
    -0.06
    rada
    -0.06
    POSITIVE LOGITS
    es
    0.12
    (es
    0.11
    ions
    0.09
    ibility
    0.09
    xes
    0.09
    ed
    0.08
    ible
    0.08
    xing
    0.08
    ioned
    0.08
    xed
    0.08
    Activations Density 0.014%

    No Known Activations