© 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. 59961
    Prev
    Next
    INDEX
    Explanations

    references to completing forms or applications online

    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
    оваÑĢи
    -0.08
    olley
    -0.07
    dux
    -0.07
    enson
    -0.07
    ENDED
    -0.07
    eya
    -0.07
    ControlEvents
    -0.07
    vak
    -0.06
    иÑģÑģ
    -0.06
    -scripts
    -0.06
    POSITIVE LOGITS
    ohan
    0.06
     apt
    0.06
    ukan
    0.06
    uri
    0.06
     Maz
    0.06
    oir
    0.05
    onom
    0.05
    ueur
    0.05
     ri
    0.05
    erras
    0.05
    Activations Density 0.012%

    No Known Activations