© 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. 1251
    Prev
    Next
    INDEX
    Explanations

    critiques of storytelling and character development

    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
    anela
    -0.07
    cts
    -0.06
    rij
    -0.06
    ads
    -0.06
    owers
    -0.06
    ovic
    -0.06
    _DEFINED
    -0.06
    åªĴ
    -0.05
     studying
    -0.05
    .onDestroy
    -0.05
    POSITIVE LOGITS
     itself
    0.09
     its
    0.09
    Its
    0.08
     Its
    0.08
    erras
    0.07
     Explicit
    0.07
    olina
    0.07
    PÅĻÃŃ
    0.07
    explicit
    0.07
    loub
    0.07
    Activations Density 0.052%

    No Known Activations