© 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. 84015
    Prev
    Next
    INDEX
    Explanations

    expressions of sadness or unfortuante circumstances

    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
    ferred
    -0.08
    oute
    -0.07
     createState
    -0.06
    ammers
    -0.06
    CLOCKS
    -0.06
    andle
    -0.06
    Äįe
    -0.06
    reur
    -0.06
    angling
    -0.06
    и
    -0.06
    POSITIVE LOGITS
     sometimes
    0.10
     often
    0.09
    sometimes
    0.08
    often
    0.07
     many
    0.07
     Edgar
    0.06
     souvent
    0.06
     Sometimes
    0.06
     Often
    0.06
     even
    0.06
    Activations Density 0.010%

    No Known Activations