© 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. 26680
    Prev
    Next
    INDEX
    Explanations

    boolean values or flags indicating status

    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
    _mime
    -0.07
    ileged
    -0.06
     Lose
    -0.06
    ÅĽmy
    -0.06
    ipo
    -0.06
    scription
    -0.06
    ulo
    -0.06
    'u
    -0.06
    ault
    -0.06
    annah
    -0.06
    POSITIVE LOGITS
    /false
    0.07
    ä¹Ĺ
    0.07
     chy
    0.07
    åľŃ
    0.07
    lee
    0.06
    !=(
    0.06
     physic
    0.06
    outu
    0.06
    ãģĺ
    0.06
    PCI
    0.06
    Activations Density 0.004%

    No Known Activations