© 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. 74652
    Prev
    Next
    INDEX
    Explanations

    language related to challenges and critical discussions

    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
    ostÃŃ
    -0.07
    amas
    -0.06
    IFI
    -0.06
    ách
    -0.06
    zion
    -0.06
     Web
    -0.06
    fon
    -0.06
    ensen
    -0.06
    fs
    -0.06
    ipe
    -0.06
    POSITIVE LOGITS
    668
    0.07
    æ²¢
    0.07
    948
    0.07
    -Ta
    0.07
    elerin
    0.07
    upil
    0.07
    .ht
    0.06
    ClientRect
    0.06
    _capture
    0.06
    834
    0.06
    Activations Density 0.050%

    No Known Activations