© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95889
    Prev
    Next
    INDEX
    Explanations

    phrases expressing experiences or attributes related to home and comfort

    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
    ulty
    -0.08
    éŀ
    -0.07
    agh
    -0.07
    akh
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    ilon
    -0.06
    uten
    -0.06
    lon
    -0.06
    orea
    -0.06
    iew
    -0.06
    POSITIVE LOGITS
    battery
    0.07
    Battery
    0.07
    SSF
    0.07
    chia
    0.06
    elts
    0.06
     dot
    0.06
    abe
    0.06
    erli
    0.06
    audio
    0.06
    arah
    0.06
    Activations Density 0.016%

    No Known Activations