© 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. 61910
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and mourning related to lost pets

    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
    lik
    -0.07
    Ñĥди
    -0.06
    outh
    -0.06
    缤
    -0.06
    getti
    -0.06
    èĥŀ
    -0.06
     Hydra
    -0.06
     Rel
    -0.06
    á»ĭ
    -0.06
     Leopard
    -0.06
    POSITIVE LOGITS
    alarm
    0.07
    YN
    0.07
    antha
    0.06
    ixe
    0.06
    ifes
    0.06
     Leonard
    0.06
     aging
    0.06
    olio
    0.06
     retirement
    0.06
    antics
    0.06
    Activations Density 0.016%

    No Known Activations