© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103858
    Prev
    Next
    INDEX
    Explanations

    instances of cancellations and related terms

    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
    phin
    -0.07
    osten
    -0.06
    adro
    -0.06
    _firestore
    -0.06
    peria
    -0.06
    ghi
    -0.06
    rrha
    -0.06
    anki
    -0.06
    tero
    -0.06
     Howell
    -0.06
    POSITIVE LOGITS
     entire
    0.07
    æģ¯
    0.07
    ucci
    0.07
     altogether
    0.07
    @js
    0.06
    emplates
    0.06
    нимаÑĤÑĮ
    0.06
     Ùħرات
    0.06
    責
    0.06
    /GPL
    0.06
    Activations Density 0.026%

    No Known Activations