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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5437
    Prev
    Next
    INDEX
    Explanations

    terms related to bonus content or additional features

    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
    ilet
    -0.07
    ogl
    -0.07
    ]=>
    -0.06
    upon
    -0.06
    uch
    -0.06
    put
    -0.06
    eo
    -0.06
    же
    -0.06
    patrick
    -0.06
    оÑıн
    -0.06
    POSITIVE LOGITS
    -extra
    0.08
    feature
    0.08
     feature
    0.08
     extras
    0.07
     bonus
    0.07
     features
    0.07
     points
    0.07
    upertino
    0.07
     ninth
    0.07
     EXTRA
    0.07
    Activations Density 0.002%

    No Known Activations