© 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. 87653
    Prev
    Next
    INDEX
    Explanations

    instances of the word "had."

    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
     currently
    -0.08
    currently
    -0.08
    conde
    -0.08
    ongo
    -0.08
    DDL
    -0.08
    vál
    -0.07
     äºĨ
    -0.07
     now
    -0.07
    OMET
    -0.07
    datatable
    -0.07
    POSITIVE LOGITS
     originally
    0.10
     earlier
    0.08
    nt
    0.08
     initially
    0.07
    /is
    0.07
     previously
    0.07
    ness
    0.07
    ÅĽmy
    0.07
     hoped
    0.07
    rian
    0.07
    Activations Density 0.074%

    No Known Activations