© 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. 78821
    Prev
    Next
    INDEX
    Explanations

    phrases related to logistical details and services, particularly in the context of moving or relocation

    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
     etc
    -0.07
    olley
    -0.07
    227
    -0.06
    OLUM
    -0.06
    olum
    -0.06
    449
    -0.06
    ensburg
    -0.06
    cript
    -0.06
    Batch
    -0.06
    222
    -0.06
    POSITIVE LOGITS
    ारण
    0.07
    ìļĶ
    0.07
    ĶåĽŀ
    0.07
    side
    0.07
    ãģıãģł
    0.07
    acro
    0.07
    oto
    0.06
    ór
    0.06
    oro
    0.06
    /apps
    0.06
    Activations Density 0.014%

    No Known Activations