© 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 EvalsExportsinterp-engineNEWAPI 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. 86664
    Prev
    Next
    INDEX
    Explanations

    discussions about legal issues and reference letters

    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
    تÙĨ
    -0.07
    ente
    -0.06
    ey
    -0.06
    CLUDING
    -0.06
    eman
    -0.06
    adlo
    -0.06
     stretch
    -0.06
    stride
    -0.05
    pressor
    -0.05
    ofday
    -0.05
    POSITIVE LOGITS
     circumstances
    0.20
     conditions
    0.19
     situations
    0.17
     Conditions
    0.16
    conditions
    0.16
    Conditions
    0.15
     circumstance
    0.14
     occasions
    0.14
     CONDITIONS
    0.14
     scenarios
    0.12
    Activations Density 0.144%

    No Known Activations