© 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. 17-LLAMASCOPE-RES-131K
    11. 87646
    Prev
    Next
    INDEX
    Explanations

    structured data or items related to specific 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
    iger
    -0.07
    stadt
    -0.07
    arella
    -0.07
    icros
    -0.07
    &T
    -0.06
    ermalink
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    prung
    -0.06
    oured
    -0.06
    EEDED
    -0.06
    POSITIVE LOGITS
    ads
    0.07
    Í
    0.06
     kıl
    0.06
     æĿ¡
    0.06
    uddy
    0.06
    наÑĢ
    0.06
     refer
    0.06
     refere
    0.06
    ilm
    0.06
    /sl
    0.06
    Activations Density 0.078%

    No Known Activations