© 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. 92747
    Prev
    Next
    INDEX
    Explanations

    terms related to specific languages, particularly focusing on attributes of those 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
    ebo
    -0.08
    iç
    -0.08
    oil
    -0.07
    oq
    -0.07
    aż
    -0.07
    eus
    -0.07
    abbo
    -0.07
    utomation
    -0.07
    zie
    -0.07
    hit
    -0.07
    POSITIVE LOGITS
    (es
    0.10
    keit
    0.08
    spr
    0.08
    dom
    0.08
    ness
    0.07
    s
    0.07
    -speaking
    0.07
    аÐ
    0.06
    urd
    0.06
    spe
    0.06
    Activations Density 0.005%

    No Known Activations