© 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. 17624
    Prev
    Next
    INDEX
    Explanations

    references to military tasks and achievements

    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
    ForResource
    -0.07
    lech
    -0.07
    ίγ
    -0.06
     içi
    -0.06
    aub
    -0.06
    roz
    -0.06
    stroy
    -0.06
    erve
    -0.06
    rip
    -0.06
    -,
    -0.06
    POSITIVE LOGITS
    -and
    0.20
     &
    0.19
    &
    0.16
    _and
    0.15
    ï¼Ĩ
    0.15
     And
    0.14
     &↵
    0.13
    &B
    0.13
    And
    0.12
    &D
    0.12
    Activations Density 0.205%

    No Known Activations