© 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. 5-LLAMASCOPE-RES-131K
    11. 126804
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities in a mathematical or coding context

    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
    ends
    -0.07
    vac
    -0.07
    essel
    -0.06
    STS
    -0.06
    vale
    -0.06
    GenerationStrategy
    -0.06
    使
    -0.06
    /umd
    -0.06
    gia
    -0.06
     Kob
    -0.05
    POSITIVE LOGITS
    aphore
    0.07
    деÑĤ
    0.06
    teen
    0.06
    ibri
    0.06
    bé
    0.06
    á»Ļi
    0.06
    _CNTL
    0.06
    gien
    0.06
    atel
    0.06
    anford
    0.06
    Activations Density 0.040%

    No Known Activations