© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 125155
    Prev
    Next
    INDEX
    Explanations

    references to online discussions and bug reports

    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
    :CGRect
    -0.07
     Www
    -0.07
    ofs
    -0.07
    umpt
    -0.06
     tomorrow
    -0.06
    apses
    -0.06
     Fact
    -0.06
    ãĥŃãĥ¼
    -0.06
    .www
    -0.06
    /catalog
    -0.06
    POSITIVE LOGITS
     thread
    0.07
     therein
    0.07
     discuss
    0.07
     threads
    0.07
    ģm
    0.06
    _THREAD
    0.06
     Thread
    0.06
     posts
    0.06
    ERY
    0.06
    åħ¶ä¸Ń
    0.06
    Activations Density 0.012%

    No Known Activations