© 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. 90345
    Prev
    Next
    INDEX
    Explanations

    locations and expressions of widespread or global movement

    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
    edic
    -0.07
    andan
    -0.07
    eland
    -0.07
    .gdx
    -0.07
    辺
    -0.07
    angu
    -0.07
    peria
    -0.07
    ame
    -0.07
    idar
    -0.07
    itar
    -0.07
    POSITIVE LOGITS
     اÙĦعاÙĦÙħ
    0.07
     Europe
    0.07
     world
    0.07
     mundo
    0.07
    world
    0.06
    é±
    0.06
    .stamp
    0.06
    ToWorld
    0.06
    Bell
    0.06
    Signature
    0.06
    Activations Density 0.015%

    No Known Activations