© 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. 3310
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to smart devices and their functionalities

    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
     cal
    -0.06
     Cal
    -0.06
    stan
    -0.05
    ÏĨοÏģ
    -0.05
    hea
    -0.05
    haft
    -0.05
    cal
    -0.05
     é¡
    -0.05
    chine
    -0.05
     count
    -0.05
    POSITIVE LOGITS
    _door
    0.08
    eÄį
    0.08
     doors
    0.08
    éŨ
    0.07
    -Za
    0.07
     baise
    0.07
    Door
    0.07
    icari
    0.07
     Doors
    0.07
     à¤ľà¤Ĺ
    0.07
    Activations Density 0.003%

    No Known Activations