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. 22-LLAMASCOPE-RES-131K
    6. 5557
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions

    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
    endir
    -0.08
    angent
    -0.07
    claimer
    -0.07
    IENTATION
    -0.07
    otas
    -0.07
    jvu
    -0.07
    Ñħа
    -0.07
    odzi
    -0.07
    jar
    -0.07
    OLON
    -0.07
    POSITIVE LOGITS
     cas
    0.07
    upal
    0.06
    Ħ
    0.06
    Ñĩин
    0.06
    اÙĦÙĩ
    0.06
    384
    0.05
     bureaucr
    0.05
    اÙĦØ©
    0.05
     imm
    0.05
    _OVER
    0.05
    Activations Density 0.047%

    No Known Activations