© 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 EvalsExportsinterp-engineNEWAPI 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. 15015
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to travel and outdoor experiences

    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
     söz
    -0.07
    æµħ
    -0.07
    Ñĥки
    -0.07
    .portal
    -0.07
    ган
    -0.06
    uguay
    -0.06
    alama
    -0.06
    夫
    -0.06
    ->__
    -0.06
    ãĥĭãĥ¥
    -0.06
    POSITIVE LOGITS
    oria
    0.07
     Compound
    0.07
     compound
    0.07
    istor
    0.06
    onium
    0.06
    oleon
    0.06
     destinationViewController
    0.06
    acman
    0.06
    /crypto
    0.06
     ped
    0.06
    Activations Density 0.003%

    No Known Activations