© 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. 117967
    Prev
    Next
    INDEX
    Explanations

    instances of the word "battle" and its variations, indicating themes of conflict or competition

    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
    ignet
    -0.07
    oya
    -0.07
    krom
    -0.07
    eming
    -0.07
     Rowe
    -0.06
     Ames
    -0.06
    iên
    -0.06
    ofs
    -0.06
    ofil
    -0.06
     Mou
    -0.06
    POSITIVE LOGITS
    NewLabel
    0.08
    uing
    0.07
    ries
    0.06
     against
    0.06
     poor
    0.06
    ains
    0.06
    pline
    0.06
    tempt
    0.06
    adows
    0.06
    eral
    0.06
    Activations Density 0.006%

    No Known Activations