© 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. 103599
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential or notable moments

    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
    leh
    -0.07
    .TabControl
    -0.07
     reconciliation
    -0.06
    FieldValue
    -0.06
    Contr
    -0.06
    oint
    -0.06
     Contr
    -0.06
     konkrét
    -0.06
    ÙĦÛĮÙĩ
    -0.06
    rant
    -0.06
    POSITIVE LOGITS
    kara
    0.07
    ContentSize
    0.06
     prior
    0.06
    edback
    0.06
    nict
    0.06
    jee
    0.06
    ffffffff
    0.06
     toItem
    0.06
    äre
    0.06
    mil
    0.06
    Activations Density 0.000%

    No Known Activations