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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 96115
    Prev
    Next
    INDEX
    Explanations

    references to ports and terminals

    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
    udas
    -0.07
    reme
    -0.07
    ulo
    -0.07
     Stam
    -0.07
    _KERNEL
    -0.06
    usive
    -0.06
    ptype
    -0.06
    bish
    -0.06
    amics
    -0.06
    ãĥ³ãĥĹ
    -0.06
    POSITIVE LOGITS
     facility
    0.06
    onaut
    0.06
    ä¸ĺ
    0.06
     quali
    0.06
    éĭ¼
    0.06
    PLATFORM
    0.06
    ikal
    0.06
     bond
    0.06
    ĩ
    0.06
    .dispatcher
    0.06
    Activations Density 0.006%

    No Known Activations