© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71077
    Prev
    Next
    INDEX
    Explanations

    attributes and descriptions of places and locations

    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
    oux
    -0.06
    alker
    -0.06
    çĿ
    -0.06
    bane
    -0.06
    ennon
    -0.06
     Kültür
    -0.06
    áš
    -0.06
    .roll
    -0.06
    urma
    -0.06
    uglify
    -0.06
    POSITIVE LOGITS
    mue
    0.07
    .swap
    0.07
    zik
    0.06
    iga
    0.06
     èĩªåĬ¨çĶŁæĪIJ
    0.06
    ¼
    0.06
    uck
    0.06
    uss
    0.06
    Ñıк
    0.06
    Else
    0.06
    Activations Density 0.002%

    No Known Activations