© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126204
    Prev
    Next
    INDEX
    Explanations

    references to personal journeys or paths

    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
     McMahon
    -0.07
    timeofday
    -0.07
    MainThread
    -0.07
    ÃŃrk
    -0.07
    launcher
    -0.07
    ocale
    -0.06
    locales
    -0.06
    pedia
    -0.06
    严
    -0.06
    .bo
    -0.06
    POSITIVE LOGITS
     journey
    0.16
     Journey
    0.11
     path
    0.11
    jour
    0.10
     route
    0.10
     journeys
    0.08
     along
    0.08
     voyage
    0.08
     trip
    0.08
    ourney
    0.07
    Activations Density 0.090%

    No Known Activations