© 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 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. 118813
    Prev
    Next
    INDEX
    Explanations

    instances of the word "finish" and its variations, indicating a focus on completion and closure

    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
    /from
    -0.08
     disple
    -0.07
    097
    -0.07
    onna
    -0.07
    Ñģам
    -0.07
    GING
    -0.06
    holding
    -0.06
    apa
    -0.06
    AW
    -0.06
     Dix
    -0.06
    POSITIVE LOGITS
    elman
    0.10
    agner
    0.08
    AllWindows
    0.07
    ãĤ¯ãĥĪ
    0.07
    angent
    0.07
     off
    0.07
     xong
    0.07
     up
    0.07
    ê³µë¶Ģ
    0.07
    iversit
    0.06
    Activations Density 0.016%

    No Known Activations