© 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. 29460
    Prev
    Next
    INDEX
    Explanations

    academic terminology and concepts related to analysis and progress in various fields

    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
    leo
    -0.08
    彦
    -0.07
    alth
    -0.07
    OU
    -0.07
    ERV
    -0.07
    åĨµ
    -0.07
     Fiesta
    -0.07
    ÑĢеÑĤ
    -0.07
     Paladin
    -0.07
    bum
    -0.06
    POSITIVE LOGITS
     usage
    0.07
     Hil
    0.07
    angan
    0.07
    _usage
    0.06
     things
    0.06
    psilon
    0.06
     impr
    0.06
     ("
    0.06
    pin
    0.06
     inconvenient
    0.06
    Activations Density 0.001%

    No Known Activations