© 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. 126382
    Prev
    Next
    INDEX
    Explanations

    locations and significant emotional 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
    adesh
    -0.07
    '#
    -0.06
    awi
    -0.06
    onden
    -0.06
    ové
    -0.06
    aint
    -0.06
    ellas
    -0.06
    izik
    -0.06
     Tape
    -0.06
    oya
    -0.06
    POSITIVE LOGITS
    nem
    0.07
    jeme
    0.06
     Og
    0.06
    ture
    0.06
     shemale
    0.06
    ÙĦÙĩ
    0.06
     çģ
    0.06
     Martial
    0.06
    unca
    0.06
    oggler
    0.06
    Activations Density 0.000%

    No Known Activations