© 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. 9-LLAMASCOPE-RES-131K
    11. 98345
    Prev
    Next
    INDEX
    Explanations

    references to orientation and related concepts

    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
    enger
    -0.07
    ower
    -0.07
    alian
    -0.07
    浦
    -0.06
    ova
    -0.06
    ets
    -0.06
    ccess
    -0.06
    coal
    -0.06
    ard
    -0.06
    ieron
    -0.06
    POSITIVE LOGITS
    ally
    0.09
    ephir
    0.07
    yaw
    0.07
    emple
    0.07
    raž
    0.07
    ABCDEFG
    0.07
    ório
    0.07
    ÛĮÙĨÚ¯
    0.07
    iap
    0.07
    ınd
    0.07
    Activations Density 0.010%

    No Known Activations