© 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. 85449
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progress or distance related to future goals

    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
    isku
    -0.07
    quist
    -0.07
    agento
    -0.07
     Westbrook
    -0.07
    átis
    -0.06
    lagen
    -0.06
    geme
    -0.06
    pra
    -0.06
    átek
    -0.06
    ležit
    -0.06
    POSITIVE LOGITS
     yet
    0.09
     still
    0.07
    yet
    0.07
    ANDOM
    0.07
    ãģ¾ãģł
    0.07
    ãĥĭãĥ¼
    0.07
     Still
    0.07
    iteli
    0.07
    rál
    0.07
     improvement
    0.07
    Activations Density 0.004%

    No Known Activations