© 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. 87391
    Prev
    Next
    INDEX
    Explanations

    references to data modeling and process management

    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
    ulong
    -0.07
    .Statement
    -0.06
    xing
    -0.06
    ablish
    -0.06
    PEC
    -0.05
     FORE
    -0.05
    IES
    -0.05
    eness
    -0.05
    _foreign
    -0.05
     protocols
    -0.05
    POSITIVE LOGITS
    flows
    0.08
    nio
    0.07
    ForResult
    0.07
    .bpm
    0.07
    (flow
    0.07
    orz
    0.07
    dfa
    0.07
    Flow
    0.07
     !***
    0.06
    _EDEFAULT
    0.06
    Activations Density 0.003%

    No Known Activations