© 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. 17-LLAMASCOPE-RES-131K
    11. 28572
    Prev
    Next
    INDEX
    Explanations

    phrases indicating categories, types, or classes related to various subjects

    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
    croft
    -0.07
    ognito
    -0.06
    lej
    -0.06
    129
    -0.06
     amount
    -0.06
    uder
    -0.06
    /error
    -0.06
    507
    -0.06
    veral
    -0.06
    åĩłä¸ª
    -0.06
    POSITIVE LOGITS
    kara
    0.07
    iffin
    0.07
    olly
    0.07
    åŀĭ
    0.07
    ÑĤÑĮ
    0.07
    ipple
    0.07
    ÑĢиÑģ
    0.07
    RIX
    0.07
    ulty
    0.06
     Opr
    0.06
    Activations Density 0.022%

    No Known Activations