© 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. 93341
    Prev
    Next
    INDEX
    Explanations

    the word "ahead" and expressions related to future plans or considerations

    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
     OPS
    -0.07
    odi
    -0.07
    bet
    -0.06
    opa
    -0.06
     Nora
    -0.06
    ths
    -0.06
    agan
    -0.06
    overs
    -0.06
    acket
    -0.05
    mes
    -0.05
    POSITIVE LOGITS
    |int
    0.08
     bevor
    0.08
    oyo
    0.07
    )$_
    0.07
     Curtain
    0.07
    onation
    0.07
    ucker
    0.07
    canf
    0.07
    adratic
    0.07
    yum
    0.07
    Activations Density 0.004%

    No Known Activations