Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76569
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    láda
    -0.06
     bridge
    -0.06
    nbsp
    -0.06
    erson
    -0.06
    otos
    -0.06
    oto
    -0.06
     col
    -0.06
    uling
    -0.06
    lrt
    -0.06
     iteration
    -0.06
    POSITIVE LOGITS
    nam
    0.08
    êu
    0.07
     ÙĪØ§ÙĦتÙĬ
    0.07
    onto
    0.07
    åı«
    0.07
    called
    0.07
     ÙħÛĮÙĦادÛĮ
    0.07
     called
    0.06
    ornings
    0.06
    óz
    0.06
    Activations Density 0.068%

    No Known Activations