© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103917
    Prev
    Next
    INDEX
    Explanations

    animal-related terms and their interactions

    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
    è´¨
    -0.07
    ór
    -0.07
    619
    -0.06
    ÏĦει
    -0.06
     Dog
    -0.06
    acf
    -0.06
    724
    -0.06
    -Sah
    -0.06
    zos
    -0.06
    ÏħÏĩ
    -0.06
    POSITIVE LOGITS
    /she
    0.07
    /small
    0.07
    kin
    0.07
    -human
    0.07
    iform
    0.06
    /cat
    0.06
    idlo
    0.06
    eyed
    0.06
    innen
    0.06
     Brid
    0.06
    Activations Density 0.046%

    No Known Activations