© 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. 5-LLAMASCOPE-RES-131K
    11. 126782
    Prev
    Next
    INDEX
    Explanations

    phrases indicating spatial or situational boundaries

    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
    bao
    -0.07
    aminer
    -0.07
    nis
    -0.07
    rap
    -0.07
    ocoa
    -0.07
    hee
    -0.07
    /cms
    -0.07
    ogo
    -0.06
    lon
    -0.06
    ech
    -0.06
    POSITIVE LOGITS
     overall
    0.08
    pter
    0.07
    ÑĢÑĥн
    0.07
    urrection
    0.06
     bounds
    0.06
     Oswald
    0.06
    aint
    0.06
     dor
    0.06
    ायà¤ķ
    0.06
     asp
    0.05
    Activations Density 0.011%

    No Known Activations