© 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. 83136
    Prev
    Next
    INDEX
    Explanations

    numerical data reflecting measurements or statistics

    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
    ora
    -0.07
    کتر
    -0.07
    ilee
    -0.07
    omez
    -0.07
    antee
    -0.07
    ience
    -0.06
    _INITIALIZER
    -0.06
    -Semit
    -0.06
    .Compiler
    -0.06
    olest
    -0.06
    POSITIVE LOGITS
    bies
    0.08
    teenth
    0.08
    bie
    0.07
     Dup
    0.06
    ï¸ı
    0.06
    edia
    0.06
    utom
    0.06
    isle
    0.06
    \OptionsResolver
    0.06
    .au
    0.06
    Activations Density 0.031%

    No Known Activations