© 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. 90050
    Prev
    Next
    INDEX
    Explanations

    references to certification exams and training materials

    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
     Anchor
    -0.06
    .hs
    -0.06
     Duty
    -0.06
     Pitch
    -0.06
    oom
    -0.06
    aklı
    -0.06
    468
    -0.06
    ç³»
    -0.06
    ä¼
    -0.06
    TEMPL
    -0.05
    POSITIVE LOGITS
     CWE
    0.08
    adele
    0.07
     ÏĢÏģα
    0.07
    ypass
    0.07
     Boyle
    0.07
    atest
    0.07
     Mug
    0.07
    imal
    0.07
     BRA
    0.06
    ommen
    0.06
    Activations Density 0.009%

    No Known Activations