© 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. 71577
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs, classes, and methods related to various frameworks or libraries

    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
    isz
    -0.07
    :
    -0.06
     =
    -0.06
     
    -0.06
     Naz
    -0.06
     –
    -0.06
    etest
    -0.06
    aten
    -0.06
     inde
    -0.05
     -
    -0.05
    POSITIVE LOGITS
    Ħĸ
    0.08
    \base
    0.08
    /Base
    0.07
    ableObject
    0.07
     Ãľl
    0.07
    abcdefghijklmnop
    0.07
    uteur
    0.07
    ibase
    0.07
    UNUSED
    0.07
    sWith
    0.07
    Activations Density 0.019%

    No Known Activations