© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 88172
    Prev
    Next
    INDEX
    Explanations

    locations and references to movement or travel

    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
    ãĥ«ãĥķ
    -0.08
    azzi
    -0.07
    alm
    -0.07
    ULAR
    -0.07
    akah
    -0.07
    سÙĪ
    -0.07
    бе
    -0.07
    fty
    -0.06
    issan
    -0.06
    onse
    -0.06
    POSITIVE LOGITS
     throughout
    0.07
    ãĤ¯ãĥĪ
    0.07
     deleg
    0.06
     from
    0.06
    XmlNode
    0.06
     backgrounds
    0.06
     abroad
    0.06
    롤
    0.06
     elsewhere
    0.06
     everywhere
    0.06
    Activations Density 0.015%

    No Known Activations