Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93830
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings typically associated with cryptographic keys

    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
    Та
    -0.07
    vale
    -0.07
    iel
    -0.07
    120
    -0.07
    ibe
    -0.07
    kk
    -0.07
    ventus
    -0.07
    ucks
    -0.06
    ibi
    -0.06
    elm
    -0.06
    POSITIVE LOGITS
    å¹¹ç·ļ
    0.06
    ãĤ¤ãĤº
    0.06
    dent
    0.06
    .visualization
    0.06
    ãĥ¼ãĥijãĥ¼
    0.06
    ITLE
    0.06
    /****************************************************************************↵
    0.06
    .Atomic
    0.06
     Kaynak
    0.06
    ĨĴ
    0.06
    Activations Density 0.011%

    No Known Activations