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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 124601
    Prev
    Next
    INDEX
    Explanations

    the use of "to" in various contexts related to objectives or actions

    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
     premi
    -0.07
    pear
    -0.07
     mans
    -0.06
    _phys
    -0.06
     bÅĻez
    -0.06
     elucid
    -0.06
     Xt
    -0.06
    رس
    -0.06
     Ama
    -0.06
     dó
    -0.06
    POSITIVE LOGITS
    WEEN
    0.07
    ĨĴ
    0.07
    bage
    0.07
    hetto
    0.07
    AlmostEqual
    0.07
    ROTO
    0.06
    éīĦéģĵ
    0.06
    ropa
    0.06
     conservatism
    0.06
    ighet
    0.06
    Activations Density 0.066%

    No Known Activations