© 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. 71110
    Prev
    Next
    INDEX
    Explanations

    conditional phrases expressing possibility or advisability

    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
    GLOSS
    -0.07
    /software
    -0.07
    podob
    -0.06
     mastur
    -0.06
     dosp
    -0.06
    ifi
    -0.06
    ãģĺ
    -0.06
    Å¡il
    -0.06
     saja
    -0.06
    íķĢ
    -0.06
    POSITIVE LOGITS
    andi
    0.07
    kh
    0.07
    vasion
    0.06
    lass
    0.06
    undle
    0.06
     Boss
    0.06
     Fres
    0.06
    ZeroWidthSpace
    0.06
    obus
    0.06
    ega
    0.06
    Activations Density 0.032%

    No Known Activations