© 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. 77025
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating recognition of notable achievements and distinguished individuals

    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
    (æľ¨
    -0.09
    apor
    -0.08
    alez
    -0.07
    olis
    -0.07
    oyer
    -0.07
    ávÄĽ
    -0.07
    eler
    -0.07
    filer
    -0.07
    åįĩ
    -0.07
    å®Ļ
    -0.07
    POSITIVE LOGITS
     figure
    0.08
     among
    0.08
    ech
    0.07
     member
    0.07
     modem
    0.06
     person
    0.06
     amongst
    0.06
     gating
    0.06
     contemporary
    0.06
    gate
    0.06
    Activations Density 0.019%

    No Known Activations