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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61283
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" in various contexts, indicating actions, purposes, or directions

    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
    ctic
    -0.08
     ÑĦÑĥнда
    -0.08
    iquement
    -0.07
    awl
    -0.07
    åĭ¤
    -0.07
    ĺ认
    -0.07
    izr
    -0.07
    ands
    -0.07
    azers
    -0.07
    éĢģæĸĻçĦ¡æĸĻ
    -0.07
    POSITIVE LOGITS
    758
    0.06
     ÑĤов
    0.06
     Sche
    0.06
    /#
    0.06
    ank
    0.06
     aktivit
    0.05
     mặt
    0.05
     Hank
    0.05
     неÑĹ
    0.05
     Cue
    0.05
    Activations Density 0.040%

    No Known Activations