© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95107
    Prev
    Next
    INDEX
    Explanations

    dominant or frequently referenced entities and common characteristics in various contexts

    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
    itto
    -0.07
    enic
    -0.06
    ARGIN
    -0.06
     ra
    -0.06
    aghan
    -0.06
     there
    -0.06
    gone
    -0.06
    idable
    -0.06
    beg
    -0.06
     ka
    -0.06
    POSITIVE LOGITS
    LETE
    0.07
    orgh
    0.07
    ipp
    0.07
    ηÏĤ
    0.07
    asaki
    0.07
    awi
    0.06
    indr
    0.06
     ÄĮer
    0.06
    arb
    0.06
    inline
    0.06
    Activations Density 0.032%

    No Known Activations