© 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. 15058
    Prev
    Next
    INDEX
    Explanations

    references to timeframes and durations

    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
    ahn
    -0.07
    317
    -0.06
     tonight
    -0.06
    rael
    -0.06
     Gerr
    -0.06
    097
    -0.06
    etu
    -0.06
    eta
    -0.05
     dumb
    -0.05
    imb
    -0.05
    POSITIVE LOGITS
    ispiel
    0.09
    ÙĬÙĦاد
    0.08
    ë§Īëĭ¤
    0.07
    iode
    0.07
    è¢ĭ
    0.07
    دÙĪد
    0.07
     Há»
    0.07
    StackNavigator
    0.07
    stride
    0.07
    HostException
    0.07
    Activations Density 0.030%

    No Known Activations