© 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. 17928
    Prev
    Next
    INDEX
    Explanations

    statements regarding personal discomfort and adjustment needs

    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
    CLU
    -0.07
    mlink
    -0.07
    idlo
    -0.07
    readcr
    -0.07
    ç©
    -0.07
    iken
    -0.07
     publicity
    -0.06
    arshal
    -0.06
    inki
    -0.06
    oriously
    -0.06
    POSITIVE LOGITS
     constantly
    0.06
    ä¸įå¾Ĺ
    0.06
     constant
    0.06
     Fig
    0.06
     Brennan
    0.05
     bunch
    0.05
    quiv
    0.05
     recourse
    0.05
     strategically
    0.05
     Dow
    0.05
    Activations Density 0.040%

    No Known Activations