© 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. 84241
    Prev
    Next
    INDEX
    Explanations

    discussions about standards and conduct in competitive contexts

    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
    roller
    -0.07
    amiliar
    -0.07
    bler
    -0.06
    ekler
    -0.06
    orrent
    -0.06
    EOF
    -0.06
    ög
    -0.06
    umpt
    -0.06
     rollers
    -0.06
     Relatives
    -0.06
    POSITIVE LOGITS
    Code
    0.07
     player
    0.07
    code
    0.07
     codes
    0.07
    cod
    0.07
     cod
    0.07
     locker
    0.07
     Code
    0.06
     PyTuple
    0.06
    decor
    0.06
    Activations Density 0.003%

    No Known Activations