© 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. 98735
    Prev
    Next
    INDEX
    Explanations

    programming code segments or syntax

    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
    isas
    -0.07
     floors
    -0.07
    Mathf
    -0.06
    icens
    -0.06
     jenis
    -0.06
    edges
    -0.06
    OLF
    -0.06
    ocz
    -0.06
    laps
    -0.06
     gear
    -0.06
    POSITIVE LOGITS
     коÑĪ
    0.07
    upp
    0.06
    _ASSUME
    0.06
    orf
    0.06
    zos
    0.06
    ÑĤаж
    0.06
    uro
    0.06
    .MixedReality
    0.06
     rov
    0.06
    çĥĪ
    0.06
    Activations Density 0.003%

    No Known Activations