© 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. 9-LLAMASCOPE-RES-131K
    11. 98548
    Prev
    Next
    INDEX
    Explanations

    phrases related to monetary values or financial transactions

    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
    igy
    -0.07
     OnCollision
    -0.06
     exp
    -0.06
    é
    -0.05
     fog
    -0.05
    Ãļ
    -0.05
    atos
    -0.05
     tÆ°
    -0.05
    806
    -0.05
    hee
    -0.05
    POSITIVE LOGITS
    «a
    0.07
    corp
    0.07
    assa
    0.07
    uben
    0.07
    CrLf
    0.07
    asa
    0.06
    _skb
    0.06
     DateTimeKind
    0.06
    ãģ®åŃIJ
    0.06
    ertura
    0.06
    Activations Density 0.008%

    No Known Activations