© 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. 79170
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to nature 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
    orry
    -0.06
    inker
    -0.06
    owl
    -0.06
    iske
    -0.06
    udd
    -0.06
    -shopping
    -0.06
    ort
    -0.06
    orgot
    -0.06
    .getExternal
    -0.06
     ÙģرÙĪ
    -0.06
    POSITIVE LOGITS
     unleash
    0.07
    unds
    0.07
    arium
    0.07
    peq
    0.07
    afs
    0.07
    ãĥ¬ãĥ³
    0.07
     bef
    0.07
     Fallen
    0.06
    fieldset
    0.06
    mailbox
    0.06
    Activations Density 0.015%

    No Known Activations