© 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. 106966
    Prev
    Next
    INDEX
    Explanations

    titles and positions held by individuals in various organizations

    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
    üf
    -0.07
    hoa
    -0.07
    aben
    -0.06
    urum
    -0.06
     gr
    -0.06
    .anim
    -0.06
     Beg
    -0.06
    mere
    -0.06
    arin
    -0.06
     ext
    -0.06
    POSITIVE LOGITS
     Company
    0.08
    åħĪçĶŁ
    0.07
    arta
    0.07
     Alpine
    0.06
    çį¨
    0.06
    Company
    0.06
     COMPANY
    0.06
     Vul
    0.06
     automát
    0.06
    rev
    0.06
    Activations Density 0.006%

    No Known Activations