© 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. 5-LLAMASCOPE-RES-131K
    11. 125942
    Prev
    Next
    INDEX
    Explanations

    language related to hospitality and inclusivity

    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
    û
    -0.06
     Arb
    -0.06
    asin
    -0.06
    ching
    -0.06
    anh
    -0.06
    inh
    -0.06
    ulle
    -0.06
     ast
    -0.06
    ango
    -0.06
    igg
    -0.06
    POSITIVE LOGITS
    ISTA
    0.08
    ÎłÏģο
    0.08
    Ïģο
    0.07
    esson
    0.07
    atar
    0.07
     Recon
    0.07
    extras
    0.07
     Tate
    0.06
    باش
    0.06
    _SECOND
    0.06
    Activations Density 0.003%

    No Known Activations