© 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. 3063
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive or uplifting information

    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
    bserv
    -0.08
    erb
    -0.08
    лÑĥг
    -0.07
    виÑī
    -0.07
    ayment
    -0.07
    UGH
    -0.07
    icens
    -0.07
     WHETHER
    -0.07
    ewn
    -0.07
    ãĢ
    -0.06
    POSITIVE LOGITS
    otto
    0.08
     hereby
    0.06
    beits
    0.06
    uzu
    0.06
     Trend
    0.06
    =""/>↵
    0.06
     æ²
    0.06
     unlike
    0.06
    andi
    0.06
     finally
    0.06
    Activations Density 0.016%

    No Known Activations