© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3818
    Prev
    Next
    INDEX
    Explanations

    references to musical releases and achievements

    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
    432
    -0.07
    apgolly
    -0.07
    å¶
    -0.06
    aÄįnÃŃ
    -0.06
    [s
    -0.06
    908
    -0.06
    à¸Ĭาว
    -0.06
    ستر
    -0.06
     unw
    -0.06
    Spin
    -0.06
    POSITIVE LOGITS
     his
    0.08
     its
    0.07
    hor
    0.07
    uting
    0.07
    hone
    0.07
     earlier
    0.06
    _processors
    0.06
    :NO
    0.06
    201
    0.06
    -sample
    0.06
    Activations Density 0.026%

    No Known Activations