© 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. 39446
    Prev
    Next
    INDEX
    Explanations

    references to other entities or examples in various 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
     же
    -0.08
    soever
    -0.07
    oret
    -0.07
    عÙĬ
    -0.06
     enough
    -0.06
     twin
    -0.06
    ito
    -0.06
    εÏģ
    -0.06
     certain
    -0.06
     -----------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
    ths
    0.09
    odom
    0.07
    ëį°
    0.07
    eru
    0.07
    tees
    0.06
    Ĥ¬
    0.06
    éru
    0.06
    AGO
    0.06
    LOTS
    0.06
     INCIDENT
    0.06
    Activations Density 0.015%

    No Known Activations