© 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. 15-LLAMASCOPE-RES-131K
    11. 90349
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical and historical contexts

    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
    ivism
    -0.07
    AMIL
    -0.07
    lessness
    -0.06
    çĬ¬
    -0.06
     stran
    -0.06
    stav
    -0.06
    istence
    -0.06
    ods
    -0.06
     Santo
    -0.06
    iro
    -0.05
    POSITIVE LOGITS
    776
    0.07
    ensis
    0.07
    enu
    0.07
    FullYear
    0.06
     Shack
    0.06
    éĮ
    0.06
    apy
    0.06
    :"-"`↵
    0.06
    Accessor
    0.06
    inkel
    0.06
    Activations Density 0.050%

    No Known Activations