© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16853
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and references related to model exports and exceptions

    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
     brief
    -0.06
     Hoa
    -0.06
    ót
    -0.06
    ammed
    -0.05
    irs
    -0.05
    itom
    -0.05
    _OVERRIDE
    -0.05
     Flores
    -0.05
     Destructor
    -0.05
    actual
    -0.05
    POSITIVE LOGITS
    Constants
    0.08
    leanup
    0.08
    .constant
    0.08
    Constant
    0.08
    Collapse
    0.08
    .constants
    0.07
    çĢ¬
    0.07
    ">//
    0.07
    Utils
    0.07
     constant
    0.07
    Activations Density 0.001%

    No Known Activations