© 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. 29645
    Prev
    Next
    INDEX
    Explanations

    action verbs related to usage and application of products or items

    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
    ura
    -0.07
    113
    -0.06
    urr
    -0.06
    že
    -0.06
     Lazy
    -0.05
     indul
    -0.05
    aurus
    -0.05
    bach
    -0.05
    iesta
    -0.05
    ulo
    -0.05
    POSITIVE LOGITS
     this
    0.13
     them
    0.10
     it
    0.10
    å®ĥ
    0.10
     these
    0.10
    *this
    0.10
    this
    0.10
    ,this
    0.10
    =this
    0.09
     nó
    0.09
    Activations Density 0.023%

    No Known Activations