© 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. 60133
    Prev
    Next
    INDEX
    Explanations

    discussions about structures and boundaries, particularly relating to cakes and protective measures

    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
     dot
    -0.07
    cke
    -0.07
    mes
    -0.06
     Dot
    -0.06
    aze
    -0.06
    328
    -0.06
    971
    -0.06
    dot
    -0.06
    å·¡
    -0.06
    ires
    -0.05
    POSITIVE LOGITS
    orp
    0.07
    opsis
    0.07
    unsupported
    0.07
    álido
    0.07
    ilty
    0.07
    ãĤ¿ãĥ«
    0.07
    éo
    0.07
    fait
    0.06
    evin
    0.06
    ĩ
    0.06
    Activations Density 0.012%

    No Known Activations