© 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. 89324
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional awareness and human experiences

    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
     Gerr
    -0.07
    ifo
    -0.07
    antry
    -0.06
     Sever
    -0.06
    798
    -0.06
    ï¸
    -0.06
    EntityType
    -0.06
    cue
    -0.06
     retrofit
    -0.06
    ajo
    -0.06
    POSITIVE LOGITS
     ******************************************************************************/↵↵
    0.07
    )(*
    0.07
    estr
    0.07
    eus
    0.06
    ANJI
    0.06
    \V
    0.06
    .decorate
    0.06
    tura
    0.06
     harmon
    0.06
    fulness
    0.06
    Activations Density 0.036%

    No Known Activations