© 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. 17701
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to"

    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
    iform
    -0.06
     PIO
    -0.06
    ائÙĩ
    -0.06
    istr
    -0.06
    etsk
    -0.06
     Spell
    -0.06
    ioni
    -0.06
    iat
    -0.05
    avan
    -0.05
    esis
    -0.05
    POSITIVE LOGITS
    ForResource
    0.07
     tubes
    0.07
    ãĤ§
    0.07
    èĥİ
    0.07
    enha
    0.07
    .go
    0.07
    با
    0.07
    çĶ¨äºİ
    0.07
    омина
    0.07
    artner
    0.07
    Activations Density 0.026%

    No Known Activations