© 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 EvalsExportsinterp-engineNEWAPI 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. 1945
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and references to telephone call cost structures

    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
     correspondence
    -0.07
    rive
    -0.06
    оÑĤÑĮ
    -0.06
    passwd
    -0.06
    DAQ
    -0.06
     Claus
    -0.06
    ibold
    -0.06
    positories
    -0.06
    orent
    -0.05
     soÄŁ
    -0.05
    POSITIVE LOGITS
    .Dial
    0.09
    callable
    0.08
    жд
    0.08
     Calling
    0.08
     callers
    0.08
    _Call
    0.08
     call
    0.07
     dial
    0.07
     Prefix
    0.07
    Calls
    0.07
    Activations Density 0.018%

    No Known Activations