© 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. 57662
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to parameters in equations

    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
    ikit
    -0.07
    _DOT
    -0.07
     Hava
    -0.06
    bersome
    -0.06
     Sofa
    -0.06
    SSIP
    -0.06
    illes
    -0.06
    lette
    -0.06
    oulder
    -0.06
    lew
    -0.06
    POSITIVE LOGITS
     prob
    0.07
     root
    0.07
    lingen
    0.06
    íĻĺ
    0.06
    _heap
    0.06
    Heap
    0.06
    _COMPAT
    0.06
    ogan
    0.06
     tut
    0.06
    ANTE
    0.06
    Activations Density 0.010%

    No Known Activations