© 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. 26601
    Prev
    Next
    INDEX
    Explanations

    phrases indicating levels of readiness or engagement

    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
    iglia
    -0.07
    lassen
    -0.07
    &q
    -0.06
    ´
    -0.06
     Lans
    -0.06
     ******************************************************************************↵
    -0.06
    .qq
    -0.06
    raquo
    -0.06
    дон
    -0.06
     Lars
    -0.05
    POSITIVE LOGITS
    ÌĨ
    0.07
    ÑĤÑĮ
    0.07
    klad
    0.07
    vg
    0.07
    es
    0.07
    ummer
    0.07
    Ì
    0.07
    lob
    0.07
    ÌĢ
    0.07
    ngör
    0.07
    Activations Density 0.044%

    No Known Activations