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. 5492
    Prev
    Next
    INDEX
    Explanations

    concepts related to narrative structure and character development

    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
    ers
    -0.08
    edReader
    -0.08
    ABLE
    -0.07
    Ø©
    -0.07
    edException
    -0.07
    gerald
    -0.07
    able
    -0.07
    edImage
    -0.07
    nt
    -0.07
    redient
    -0.06
    POSITIVE LOGITS
    ally
    0.09
     //////////////////////////////////////////////////////////////////////
    0.09
    uš
    0.08
    -ÑĤаки
    0.08
    Ùij
    0.08
    ëıĦë¡ľ
    0.07
    ativ
    0.07
    iyi
    0.07
    åª
    0.07
    cha
    0.07
    Activations Density 0.043%

    No Known Activations