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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96155
    Prev
    Next
    INDEX
    Explanations

    references to advertisement and marketing activities

    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
    rawer
    -0.08
    .sax
    -0.08
    adel
    -0.08
    bjerg
    -0.07
    igos
    -0.07
    illow
    -0.07
    ylland
    -0.07
    venes
    -0.07
    shelf
    -0.07
    odus
    -0.07
    POSITIVE LOGITS
    olist
    0.06
     exclusive
    0.06
     Vend
    0.06
     Shade
    0.06
    oya
    0.06
     Kirst
    0.06
     Statue
    0.06
    å¹²
    0.05
     Tip
    0.05
    ede
    0.05
    Activations Density 0.004%

    No Known Activations