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. 43859
    Prev
    Next
    INDEX
    Explanations

    references to weapons and their attributes or uses

    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
     lá»Ļ
    -0.07
    aland
    -0.07
    ervo
    -0.07
    ĽĪ
    -0.07
    umpt
    -0.07
    ramework
    -0.07
    _tF
    -0.07
    PROTO
    -0.07
    _AHB
    -0.06
    :\/\/
    -0.06
    POSITIVE LOGITS
     spear
    0.12
     axes
    0.12
     dag
    0.12
     staff
    0.11
     dagger
    0.11
     clubs
    0.11
     swords
    0.11
     sword
    0.10
     axe
    0.10
     pole
    0.10
    Activations Density 0.021%

    No Known Activations