© 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. 3235
    Prev
    Next
    INDEX
    Explanations

    complex concepts related to scientific modeling and satellite positioning

    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
    ominator
    -0.06
     Alphabet
    -0.06
    åį·
    -0.06
     sever
    -0.06
     insulting
    -0.06
    å£°éŁ³
    -0.06
    Ghost
    -0.06
    getDb
    -0.06
    梯
    -0.06
     pilot
    -0.05
    POSITIVE LOGITS
     quỹ
    0.08
     secular
    0.07
    æħİ
    0.07
    ottie
    0.07
     Chore
    0.07
    utin
    0.07
     Dynamics
    0.07
     Chandler
    0.06
     Lowell
    0.06
    uitka
    0.06
    Activations Density 0.023%

    No Known Activations