© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27323
    Prev
    Next
    INDEX
    Explanations

    career-related terms in the field of biology and genetics

    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
    azen
    -0.10
    çīĮ
    -0.08
    resa
    -0.08
    udev
    -0.08
    StringEncoding
    -0.08
    raya
    -0.08
    ooke
    -0.07
    imir
    -0.07
    upt
    -0.07
    insn
    -0.07
    POSITIVE LOGITS
     Abb
    0.07
     ab
    0.06
     fals
    0.06
     Hills
    0.06
     Clip
    0.06
     role
    0.06
     feas
    0.05
     Morgan
    0.05
     Bowman
    0.05
     Entry
    0.05
    Activations Density 0.031%

    No Known Activations