© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107245
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive change and uplifting sentiments

    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
    sav
    -0.07
    endon
    -0.07
    ẽ
    -0.07
    ersion
    -0.07
    erv
    -0.07
    icom
    -0.07
     Ñĩин
    -0.07
    acle
    -0.07
    uci
    -0.06
    .Level
    -0.06
    POSITIVE LOGITS
    -negative
    0.12
    /n
    0.10
    /-
    0.07
    itives
    0.07
    cly
    0.07
    -minded
    0.07
     integers
    0.07
    -feedback
    0.07
    _integer
    0.07
    IntegerField
    0.07
    Activations Density 0.014%

    No Known Activations