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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76349
    Prev
    Next
    INDEX
    Explanations

    references to document organization or archival processes

    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
    acker
    -0.07
    nth
    -0.07
    orny
    -0.06
    iquer
    -0.06
    ledo
    -0.06
    ба
    -0.06
    edad
    -0.06
    wstring
    -0.06
     vidé
    -0.06
    nam
    -0.06
    POSITIVE LOGITS
     Blog
    0.06
     blogging
    0.06
     writing
    0.06
     Writing
    0.06
    post
    0.06
    Destructor
    0.06
     magnet
    0.06
     post
    0.06
    -blog
    0.06
     Post
    0.06
    Activations Density 0.000%

    No Known Activations