© 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. 29463
    Prev
    Next
    INDEX
    Explanations

    concepts related to research methodologies and findings

    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
    hoe
    -0.06
    dock
    -0.06
    che
    -0.06
     X
    -0.06
    iances
    -0.06
    ies
    -0.06
    averse
    -0.05
    ght
    -0.05
    immer
    -0.05
    sto
    -0.05
    POSITIVE LOGITS
     herein
    0.16
     here
    0.14
    _here
    0.13
    ãģĵãģĵ
    0.13
     aquÃŃ
    0.12
    è¿ĻéĩĮ
    0.12
    here
    0.12
     aqui
    0.11
    Here
    0.11
    æľ¬
    0.11
    Activations Density 0.287%

    No Known Activations