© 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. 95886
    Prev
    Next
    INDEX
    Explanations

    phrases expressing enjoyment or positive 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
    rage
    -0.06
    AKE
    -0.06
    /scripts
    -0.06
     Lage
    -0.06
     shr
    -0.06
    lassen
    -0.06
    wit
    -0.05
    gger
    -0.05
     wa
    -0.05
    lay
    -0.05
    POSITIVE LOGITS
    BOSE
    0.08
    oriously
    0.07
    itesse
    0.07
    stras
    0.07
    _barrier
    0.06
    oenix
    0.06
    elines
    0.06
    eus
    0.06
    .sel
    0.06
    /sn
    0.06
    Activations Density 0.007%

    No Known Activations