© 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. 87196
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of migration and migratory patterns

    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
    rud
    -0.07
    hide
    -0.07
    rz
    -0.07
    Ù
    -0.07
    -hide
    -0.07
    ırak
    -0.06
    ding
    -0.06
     Bản
    -0.06
    ski
    -0.06
    isans
    -0.06
    POSITIVE LOGITS
    /local
    0.08
    arb
    0.07
    zsche
    0.06
    unner
    0.06
    urs
    0.06
    asper
    0.06
     pattern
    0.06
    ated
    0.06
    ors
    0.06
    fts
    0.06
    Activations Density 0.008%

    No Known Activations