© 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. 76870
    Prev
    Next
    INDEX
    Explanations

    numerical values related to quantities or measures

    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
     Zam
    -0.08
    oad
    -0.07
    369
    -0.06
     åī
    -0.06
    oder
    -0.06
    werk
    -0.06
    421
    -0.06
    etic
    -0.06
    essel
    -0.06
    owards
    -0.06
    POSITIVE LOGITS
     fich
    0.07
    ائع
    0.07
    PERT
    0.07
     recorded
    0.06
    hem
    0.06
    κι
    0.06
    TestMethod
    0.06
    alist
    0.06
     simp
    0.06
    chner
    0.06
    Activations Density 0.016%

    No Known Activations