© 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. 120068
    Prev
    Next
    INDEX
    Explanations

    references to health, prevention, and improvement strategies

    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
    νε
    -0.08
     Simpl
    -0.07
     ÑĥÑĩаÑģÑĤи
    -0.07
    ENU
    -0.07
    .RunWith
    -0.07
    aidu
    -0.07
    .uf
    -0.07
    Parms
    -0.07
    aeda
    -0.07
    uraa
    -0.07
    POSITIVE LOGITS
     anti
    0.10
    anti
    0.09
     Anti
    0.07
     avoidance
    0.07
     Jac
    0.07
     protection
    0.07
     immunity
    0.07
     avoiding
    0.07
     immune
    0.06
    mit
    0.06
    Activations Density 0.082%

    No Known Activations