© 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. 124167
    Prev
    Next
    INDEX
    Explanations

    references to capabilities and functionalities in various contexts

    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
    anth
    -0.07
    utherland
    -0.06
    jeta
    -0.06
    ÙĥÙĪÙĨ
    -0.06
    ุà¸Ĺà¸ĺ
    -0.06
    asaki
    -0.06
    URT
    -0.06
    ublice
    -0.06
    ãĤ¯ãĥĪ
    -0.05
     sustain
    -0.05
    POSITIVE LOGITS
     ability
    0.07
    Ability
    0.07
     Möglichkeit
    0.07
    ismus
    0.07
     possibility
    0.07
    angi
    0.06
    inium
    0.06
     αÏĥ
    0.06
     to
    0.06
    rium
    0.06
    Activations Density 0.010%

    No Known Activations