© 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. 106780
    Prev
    Next
    INDEX
    Explanations

    questions and interactive prompts related to knowledge assessment

    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
    avel
    -0.07
    aleur
    -0.07
    urai
    -0.07
     Cave
    -0.06
     NOTES
    -0.06
    ÑĨип
    -0.06
    lemen
    -0.06
    åī£
    -0.06
    Äįen
    -0.06
    verture
    -0.06
    POSITIVE LOGITS
     quiz
    0.07
     yourself
    0.06
     knowledge
    0.06
    mpi
    0.06
    eria
    0.06
     challenge
    0.06
    uku
    0.06
     Bey
    0.06
    iera
    0.06
     score
    0.06
    Activations Density 0.008%

    No Known Activations