© 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. 93967
    Prev
    Next
    INDEX
    Explanations

    mentions of sports team achievements and accolades

    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
    ëł¹
    -0.08
     Jaune
    -0.07
    оÑĢоÑĪ
    -0.07
    оÑĤа
    -0.07
    ?=
    -0.07
    iset
    -0.07
    _TW
    -0.07
    úi
    -0.07
    ornment
    -0.07
    živ
    -0.06
    POSITIVE LOGITS
    iglia
    0.08
    ì§ľ
    0.07
    edly
    0.07
    >:</
    0.06
    ed
    0.06
    mac
    0.06
    eed
    0.06
    oon
    0.06
    ers
    0.06
    igy
    0.06
    Activations Density 0.001%

    No Known Activations