© 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. 29250
    Prev
    Next
    INDEX
    Explanations

    numerical data and measurements related to performance metrics

    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
    ,
    -0.07
    ERA
    -0.06
    ometr
    -0.06
     Saga
    -0.05
    !
    -0.05
     Wein
    -0.05
     mend
    -0.05
     land
    -0.05
     relatively
    -0.05
     unless
    -0.05
    POSITIVE LOGITS
    achu
    0.08
    CRET
    0.08
    Ñĸп
    0.08
    CLAIM
    0.07
    COMPARE
    0.07
    iec
    0.07
    ãģŀ
    0.07
    ortal
    0.07
    erek
    0.07
    ocol
    0.07
    Activations Density 0.002%

    No Known Activations