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. 43452
    Prev
    Next
    INDEX
    Explanations

    special characters and non-standard symbols in the text

    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
    Interop
    -0.06
     Kid
    -0.06
     Sew
    -0.06
    ulp
    -0.06
     Jerome
    -0.06
    interp
    -0.06
     progn
    -0.05
     Cotton
    -0.05
    č
    -0.05
    ertz
    -0.05
    POSITIVE LOGITS
     training
    0.11
     Lara
    0.10
     Alicia
    0.10
     MMA
    0.09
     trainers
    0.09
     workout
    0.09
     workouts
    0.09
     trainer
    0.09
     Training
    0.09
    training
    0.09
    Activations Density 0.003%

    No Known Activations