© 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 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. 17-LLAMASCOPE-RES-131K
    11. 118781
    Prev
    Next
    INDEX
    Explanations

    exaggerative adverbs that emphasize extremity or excess

    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
    pedia
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    emb
    -0.07
     itself
    -0.07
    uj
    -0.07
    ed
    -0.07
    edly
    -0.06
    uta
    -0.06
    able
    -0.06
    ando
    -0.06
    POSITIVE LOGITS
     îł
    0.07
    orns
    0.07
    ysi
    0.07
    amt
    0.07
    axy
    0.06
    -thirds
    0.06
    cka
    0.06
    rát
    0.06
    ullan
    0.06
    ترÛĮ
    0.06
    Activations Density 0.016%

    No Known Activations