© 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. 55759
    Prev
    Next
    INDEX
    Explanations

    active verbs or phrases associated with motion and change

    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
    лава
    -0.08
    udit
    -0.08
    -нибÑĥдÑĮ
    -0.07
    likle
    -0.07
    utsch
    -0.07
    á»ijt
    -0.07
    	Copyright
    -0.07
    siz
    -0.07
    itty
    -0.07
    aml
    -0.07
    POSITIVE LOGITS
    ed
    0.14
    ing
    0.11
    es
    0.08
    äºĨä¸Ģ
    0.08
    [s
    0.08
    sthrough
    0.08
    sWith
    0.08
    edException
    0.07
    ÂŃing
    0.07
    edBy
    0.07
    Activations Density 0.067%

    No Known Activations