© 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. 15-LLAMASCOPE-RES-131K
    11. 62350
    Prev
    Next
    INDEX
    Explanations

    the framework or structure of code, particularly function declarations and commands

    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
    iva
    -0.07
    vant
    -0.07
    arf
    -0.07
    andest
    -0.07
    asan
    -0.07
    оÑģÑĤаÑĤ
    -0.06
    lice
    -0.06
    arent
    -0.06
    umpt
    -0.06
    HU
    -0.06
    POSITIVE LOGITS
     additions
    0.08
     addTo
    0.07
     added
    0.07
    =add
    0.07
    _add
    0.07
     Add
    0.07
     insert
    0.07
    adding
    0.07
    æ·»åĬł
    0.07
     add
    0.07
    Activations Density 0.015%

    No Known Activations