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. 31-LLAMASCOPE-RES-131K
    6. 11491
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols related to measurements and data representation

    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
     (“
    -0.07
     –↵↵
    -0.06
    ,↵↵↵↵
    -0.06
    im
    -0.06
    se
    -0.06
     vX
    -0.06
    sp
    -0.06
     –↵
    -0.06
    x
    -0.06
    ih
    -0.06
    POSITIVE LOGITS
    Shot
    0.10
     Shot
    0.10
    --
    0.09
    Corner
    0.08
    Correction
    0.08
    \
    0.08
     Shots
    0.08
    <
    0.08
     Shoot
    0.08
     Shooting
    0.07
    Activations Density 0.002%

    No Known Activations