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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127058
    Prev
    Next
    INDEX
    Explanations

    affirmative or questioning statements regarding expectations or outcomes

    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
    ouns
    -0.07
    elay
    -0.07
     Wonder
    -0.06
     wonder
    -0.06
    azy
    -0.06
    iem
    -0.06
    λÏį
    -0.06
    esto
    -0.06
    uffy
    -0.06
    icip
    -0.06
    POSITIVE LOGITS
     possibility
    0.09
     odds
    0.09
     Stranger
    0.09
    åı¯èĥ½æĢ§
    0.08
     possibilities
    0.08
    dorf
    0.07
     Odds
    0.07
     chances
    0.07
    endir
    0.07
     likelihood
    0.07
    Activations Density 0.034%

    No Known Activations