© 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. 17-LLAMASCOPE-RES-131K
    6. 76972
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Sears" or variations of it

    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
    lico
    -0.08
    оналÑĮ
    -0.07
    elu
    -0.06
    verse
    -0.06
    ube
    -0.06
    yal
    -0.06
    kowski
    -0.06
    eman
    -0.06
    gor
    -0.06
    compact
    -0.06
    POSITIVE LOGITS
    uiltin
    0.08
    lings
    0.07
    ldr
    0.07
    sville
    0.07
    ucker
    0.07
    latex
    0.07
    ĶåĽŀ
    0.07
    rp
    0.07
    mamak
    0.07
    Ñģли
    0.07
    Activations Density 0.002%

    No Known Activations