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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 87416
    Prev
    Next
    INDEX
    Explanations

    structured data attributes and parameters for configuration and processing

    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
    imli
    -0.08
    .radioButton
    -0.08
    erus
    -0.07
    rog
    -0.07
    .PrimaryKey
    -0.07
     anlamda
    -0.07
    teri
    -0.07
    ÏĦÏĥ
    -0.07
     piger
    -0.07
    vá
    -0.07
    POSITIVE LOGITS
     likewise
    0.09
    dit
    0.09
     dit
    0.08
     Heating
    0.07
     Dit
    0.07
     ÑĤоже
    0.07
     Likewise
    0.06
     equally
    0.06
    Painter
    0.06
    nah
    0.06
    Activations Density 0.132%

    No Known Activations