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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74986
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions or exceptions

    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
    leur
    -0.06
     branch
    -0.06
    rey
    -0.06
     prepared
    -0.06
    _DLL
    -0.06
    Äĥr
    -0.05
    ogan
    -0.05
     hyp
    -0.05
     exc
    -0.05
    issen
    -0.05
    POSITIVE LOGITS
    otherwise
    0.09
    VarChar
    0.08
    تÙģ
    0.07
    eÄį
    0.07
     OTHERWISE
    0.07
    instanc
    0.07
    wdx
    0.07
     èĢ
    0.07
     otherwise
    0.07
    ÙĪار
    0.07
    Activations Density 0.004%

    No Known Activations