Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44437
    Prev
    Next
    INDEX
    Explanations

    concepts related to physical injury and the body

    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
    edException
    -0.06
    anut
    -0.06
     debounce
    -0.06
    quisites
    -0.05
    oltip
    -0.05
    ียà¸ĩ
    -0.05
     snippet
    -0.05
    caret
    -0.05
    enstein
    -0.05
     countdown
    -0.05
    POSITIVE LOGITS
     parts
    0.13
     areas
    0.11
     wrists
    0.11
     cheeks
    0.10
     portions
    0.10
     exposed
    0.10
     thighs
    0.10
     ankles
    0.10
     sensitive
    0.10
    parts
    0.10
    Activations Density 0.045%

    No Known Activations