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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85714
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunications and toll-free services

    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
    ifar
    -0.07
    .scalablytyped
    -0.07
    ges
    -0.07
    áš
    -0.07
    krom
    -0.07
    krv
    -0.07
     SpoleÄį
    -0.06
    oÅĪ
    -0.06
    ÃŃž
    -0.06
    ноÑĪ
    -0.06
    POSITIVE LOGITS
     domain
    0.10
     domains
    0.09
    domain
    0.09
     Domain
    0.09
    Domain
    0.08
     DOMAIN
    0.08
    -domain
    0.07
    _domain
    0.07
    (domain
    0.07
    åŁŁ
    0.07
    Activations Density 0.005%

    No Known Activations