© 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. 39345
    Prev
    Next
    INDEX
    Explanations

    phrases expressing accountability or the need for action regarding specific issues

    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
    maktan
    -0.07
    aversal
    -0.07
    izr
    -0.07
    immel
    -0.07
    volt
    -0.06
    áme
    -0.06
    /rs
    -0.06
    ChildIndex
    -0.06
    ooth
    -0.06
    raison
    -0.06
    POSITIVE LOGITS
    orks
    0.07
     actionTypes
    0.07
     aspect
    0.07
     particular
    0.07
     specific
    0.06
    roulette
    0.06
    nc
    0.06
     potential
    0.06
    itarian
    0.06
    ork
    0.06
    Activations Density 0.030%

    No Known Activations