© 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. 17-LLAMASCOPE-RES-131K
    11. 61739
    Prev
    Next
    INDEX
    Explanations

    details about characters' relationships and personal circumstances

    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
    regon
    -0.07
    egra
    -0.07
    staking
    -0.07
    aversable
    -0.07
    /goto
    -0.07
    _resource
    -0.07
     münchen
    -0.07
    alim
    -0.07
    cores
    -0.06
    illez
    -0.06
    POSITIVE LOGITS
     dating
    0.07
     bachelor
    0.07
     singles
    0.07
     Singles
    0.07
     Dating
    0.06
     Guys
    0.06
     Bachelor
    0.06
     Cup
    0.06
    alth
    0.06
    assi
    0.06
    Activations Density 0.011%

    No Known Activations