© 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. 41086
    Prev
    Next
    INDEX
    Explanations

    organizations or institutions focused on social good and data analytics

    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
     ç¤
    -0.07
    uki
    -0.07
    ensa
    -0.06
    alem
    -0.06
    unda
    -0.06
    ocom
    -0.06
    ovie
    -0.06
    ắt
    -0.06
    reon
    -0.06
    orio
    -0.06
    POSITIVE LOGITS
     research
    0.09
    research
    0.08
     researchers
    0.07
     Research
    0.07
     center
    0.07
     researching
    0.07
     centre
    0.07
    /umd
    0.07
    ATUS
    0.07
    team
    0.07
    Activations Density 0.041%

    No Known Activations