© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106333
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial services and mobile data usage

    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
     pac
    -0.06
     Lan
    -0.06
     Lear
    -0.06
     Lent
    -0.06
     materials
    -0.06
     res
    -0.06
    urm
    -0.06
    Aux
    -0.06
    voy
    -0.05
     satisf
    -0.05
    POSITIVE LOGITS
     USS
    0.08
    UNET
    0.08
    .apps
    0.07
    erç
    0.07
    UPI
    0.07
     recharge
    0.07
     unlink
    0.07
    /card
    0.07
    occo
    0.07
     Rural
    0.07
    Activations Density 0.008%

    No Known Activations