© 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. 27391
    Prev
    Next
    INDEX
    Explanations

    statements about causality and conditions

    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
    ỳ
    -0.09
    plib
    -0.09
    ofday
    -0.08
     ilan
    -0.08
    .localization
    -0.08
    زار
    -0.08
    umerator
    -0.08
    imonials
    -0.08
     -------------------------------------------------------------------------
    -0.08
    .Formatter
    -0.08
    POSITIVE LOGITS
    ahlen
    0.06
     ne
    0.06
    sis
    0.05
    \Active
    0.05
    ↵
    0.05
    -pro
    0.05
    ais
    0.05
    peat
    0.05
    -↵
    0.05
     over
    0.05
    Activations Density 0.241%

    No Known Activations