© 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. 9-LLAMASCOPE-RES-131K
    11. 94499
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to heat and heating processes

    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
     trace
    -0.06
    cpt
    -0.06
    usize
    -0.06
    ac
    -0.06
    DL
    -0.05
     Werk
    -0.05
     member
    -0.05
    ound
    -0.05
     æĽ
    -0.05
     i
    -0.05
    POSITIVE LOGITS
    ÅĻad
    0.10
    ãĥ³ãĥģ
    0.08
    oise
    0.08
    oreach
    0.08
    uitka
    0.08
    /***/
    0.07
    /weather
    0.07
    Äįer
    0.07
    oine
    0.07
    -pill
    0.07
    Activations Density 0.014%

    No Known Activations