© 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. 105060
    Prev
    Next
    INDEX
    Explanations

    numerical values or prices related to financial 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
    efa
    -0.07
    otto
    -0.06
    MBER
    -0.06
    vely
    -0.06
    r
    -0.06
    ubby
    -0.06
    :
    -0.06
    ledon
    -0.06
    ooter
    -0.06
    ÏģαÏĤ
    -0.05
    POSITIVE LOGITS
     ActionTypes
    0.07
    æĨ
    0.07
    Compose
    0.07
    compose
    0.06
    instein
    0.06
    εÏĦ
    0.06
    ettel
    0.06
    fection
    0.06
    ÑĪÑĮ
    0.06
    ÙĨØ´
    0.06
    Activations Density 0.002%

    No Known Activations