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. 22-LLAMASCOPE-RES-131K
    6. 5173
    Prev
    Next
    INDEX
    Explanations

    references to the name "David B." followed by various identifiers or titles

    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
    hta
    -0.08
    odem
    -0.07
    .scalajs
    -0.07
    obel
    -0.07
    oyer
    -0.07
    ohan
    -0.07
    oload
    -0.07
    inea
    -0.07
    ober
    -0.07
    cht
    -0.06
    POSITIVE LOGITS
     conce
    0.06
    zb
    0.06
     Villa
    0.06
    illa
    0.06
    .lb
    0.05
     Ow
    0.05
    shiv
    0.05
     collaps
    0.05
     Fauc
    0.05
     Sep
    0.05
    Activations Density 0.002%

    No Known Activations