© 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. 76512
    Prev
    Next
    INDEX
    Explanations

    logistical details about scheduling and access

    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
    zier
    -0.08
    ader
    -0.07
    omor
    -0.07
    ahir
    -0.06
     Tax
    -0.06
    aidu
    -0.06
     TAX
    -0.06
     tax
    -0.06
    áºŃu
    -0.06
    ught
    -0.06
    POSITIVE LOGITS
     lottery
    0.09
    thenReturn
    0.08
    _COMPLEX
    0.07
     reserv
    0.07
     reservation
    0.07
     reserva
    0.07
     reservations
    0.07
     Reservation
    0.07
    bsd
    0.07
    PERT
    0.06
    Activations Density 0.004%

    No Known Activations