© 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. 106414
    Prev
    Next
    INDEX
    Explanations

    sentences that conclude with a period

    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
    ifi
    -0.06
    /msg
    -0.06
    ypsum
    -0.06
    addock
    -0.06
    loo
    -0.06
    eyn
    -0.06
    ÑĥÑģÑĤ
    -0.06
    ETY
    -0.06
    ulk
    -0.05
    adj
    -0.05
    POSITIVE LOGITS
    111
    0.07
    erno
    0.07
    ence
    0.07
     Blur
    0.06
    399
    0.06
    sst
    0.06
     requestOptions
    0.06
     Slo
    0.06
    enity
    0.06
     Justice
    0.06
    Activations Density 0.002%

    No Known Activations