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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95887
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate difficulty or challenges in locating information or resources

    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
    illos
    -0.07
    iez
    -0.07
    eurs
    -0.07
    ierge
    -0.06
     somehow
    -0.06
    bilt
    -0.06
    /XML
    -0.06
    ADS
    -0.06
    ueur
    -0.06
     dile
    -0.06
    POSITIVE LOGITS
    utow
    0.07
    enuity
    0.07
    æ¿Ģ
    0.07
    icaid
    0.06
     CONSEQUENTIAL
    0.06
    535
    0.06
     Camb
    0.06
    edia
    0.06
     Berm
    0.06
    /ex
    0.06
    Activations Density 0.015%

    No Known Activations