© 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. 87843
    Prev
    Next
    INDEX
    Explanations

    qualitative descriptions and evaluations of various subjects

    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
    ibur
    -0.07
    ash
    -0.07
    lige
    -0.06
     feeling
    -0.06
     met
    -0.06
    oron
    -0.06
    _UD
    -0.06
    aki
    -0.06
    ãĥ¼ãĥ
    -0.06
    idan
    -0.06
    POSITIVE LOGITS
    åĥıæĺ¯
    0.07
    peror
    0.07
    lessly
    0.07
    äºİ
    0.06
    segue
    0.06
     Temper
    0.06
    chwitz
    0.06
    èĥĮ
    0.06
     lượt
    0.06
    itzer
    0.06
    Activations Density 0.072%

    No Known Activations