© 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. 125858
    Prev
    Next
    INDEX
    Explanations

    information related to authorship and organizational affiliations

    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
    uja
    -0.07
    enburg
    -0.07
    rana
    -0.07
    omics
    -0.07
    eya
    -0.07
    vais
    -0.06
    ัà¸Ĵ
    -0.06
    ports
    -0.06
    ichel
    -0.06
     Smy
    -0.06
    POSITIVE LOGITS
     org
    0.08
     institution
    0.08
    æľºæŀĦ
    0.08
     organization
    0.08
     organisation
    0.08
     responsible
    0.08
     institutions
    0.07
     organisations
    0.07
     entity
    0.07
     organizations
    0.07
    Activations Density 0.021%

    No Known Activations