© 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. 71023
    Prev
    Next
    INDEX
    Explanations

    questions and assertions about the validity of various claims and beliefs

    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
    adb
    -0.07
     excellent
    -0.06
     outstanding
    -0.06
     tem
    -0.06
    andal
    -0.06
    ani
    -0.06
    byn
    -0.06
    rena
    -0.05
     perfectly
    -0.05
    ASSES
    -0.05
    POSITIVE LOGITS
     really
    0.18
     Really
    0.17
    Really
    0.16
    really
    0.16
     wirklich
    0.15
    羣çļĦ
    0.15
     REALLY
    0.14
    æľ¬å½ĵãģ«
    0.14
     realmente
    0.14
     vraiment
    0.13
    Activations Density 0.048%

    No Known Activations