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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5304
    Prev
    Next
    INDEX
    Explanations

    code-related terms and annotations

    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
    anka
    -0.08
    úp
    -0.08
     íıIJ
    -0.07
    ei
    -0.06
    ervlet
    -0.06
    mans
    -0.06
    anch
    -0.06
     ilet
    -0.06
     Bat
    -0.06
    STS
    -0.06
    POSITIVE LOGITS
    intl
    0.07
    anni
    0.07
    911
    0.07
    vem
    0.06
    лÑıв
    0.06
    ullan
    0.06
    oload
    0.06
    jing
    0.06
    erp
    0.06
    allery
    0.06
    Activations Density 0.001%

    No Known Activations