© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 104290
    Prev
    Next
    INDEX
    Explanations

    strings that appear to be coded outputs or syntax structures typical in programming languages

    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
    éŀ
    -0.06
    afe
    -0.06
    dig
    -0.06
    anter
    -0.06
    okie
    -0.06
    OAD
    -0.06
    onas
    -0.06
    feito
    -0.06
    efe
    -0.06
     inj
    -0.06
    POSITIVE LOGITS
     Locker
    0.07
    eid
    0.07
    .AutoScaleMode
    0.07
    ãn
    0.06
    igators
    0.06
     vá»įng
    0.06
    loha
    0.06
    ẩu
    0.06
    ĨĴ
    0.06
    .toolbox
    0.06
    Activations Density 0.038%

    No Known Activations