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. 43895
    Prev
    Next
    INDEX
    Explanations

    foreign or non-English characters and symbols

    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
     ‘
    -0.13
    –and
    -0.10
    =”
    -0.10
    â̦..
    -0.10
    ‘
    -0.10
    â̦”
    -0.09
     “
    -0.09
    ’
    -0.09
     â̦.
    -0.09
     “â̦
    -0.09
    POSITIVE LOGITS
     еÑīÑij
    0.08
     Québec
    0.08
    &oacute
    0.08
    &quot
    0.08
     &#
    0.08
     Qué
    0.08
     еÑij
    0.07
     ÑģеÑĢÑĮ
    0.07
     âĢł
    0.07
     US
    0.07
    Activations Density 0.004%

    No Known Activations