© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 17297
    Prev
    Next
    INDEX
    Explanations

    parts of code or script that mark the end of a section or file

    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
    еÑĢеÑĩ
    -0.06
    mers
    -0.06
    enge
    -0.06
    orman
    -0.06
    ли
    -0.06
     exact
    -0.05
    Pr
    -0.05
     desp
    -0.05
     fing
    -0.05
    ël
    -0.05
    POSITIVE LOGITS
    trer
    0.07
    apot
    0.07
    amac
    0.07
    Slf
    0.07
    ANEL
    0.07
     thừa
    0.07
    ntp
    0.07
    ledon
    0.07
    CLUD
    0.07
    gst
    0.07
    Activations Density 0.053%

    No Known Activations