© 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. 17-LLAMASCOPE-RES-131K
    11. 85164
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, particularly cities and states

    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
    ingle
    -0.07
    ÙħاÙĦ
    -0.07
     [âĢ¦]↵
    -0.06
     [âĢ¦]
    -0.06
    swire
    -0.06
    [s
    -0.06
    gesi
    -0.06
     ÙħتØŃ
    -0.06
    cri
    -0.06
    ius
    -0.06
    POSITIVE LOGITS
    elik
    0.08
    evi
    0.07
    égor
    0.07
    connexion
    0.06
    onaut
    0.06
     vigil
    0.06
    eniable
    0.06
    amedi
    0.06
    reinterpret
    0.06
    stead
    0.06
    Activations Density 0.019%

    No Known Activations