© 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. 71635
    Prev
    Next
    INDEX
    Explanations

    discussions about context, experiences, and narratives shaping perceptions

    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
    egrity
    -0.08
    dq
    -0.07
     Thoughts
    -0.07
     compte
    -0.07
    rani
    -0.07
    ROUGH
    -0.07
    eated
    -0.07
    ανά
    -0.06
    wij
    -0.06
     dilemma
    -0.06
    POSITIVE LOGITS
     lack
    0.08
     sheer
    0.08
     natural
    0.07
     age
    0.07
     other
    0.07
    azzi
    0.07
    Elf
    0.07
     politics
    0.07
     bad
    0.07
     etc
    0.06
    Activations Density 0.032%

    No Known Activations