© 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. 40085
    Prev
    Next
    INDEX
    Explanations

    references to exam questions and related content

    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
    vey
    -0.08
     surveys
    -0.07
    آخر
    -0.06
    .CopyTo
    -0.06
    ouble
    -0.06
    éĽ
    -0.06
     YÃĸ
    -0.06
    um
    -0.06
    ombok
    -0.06
    оÐ
    -0.06
    POSITIVE LOGITS
     preparation
    0.08
     Preparation
    0.07
     prepare
    0.06
    .com
    0.06
     Training
    0.06
    nutÃŃ
    0.06
    orda
    0.06
    ær
    0.06
    érie
    0.06
    ismu
    0.06
    Activations Density 0.000%

    No Known Activations