© 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. 130164
    Prev
    Next
    INDEX
    Explanations

    phrases related to attention and public interest

    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
    asso
    -0.07
    illis
    -0.07
    estar
    -0.07
    ãĤĤãĤĬ
    -0.07
    odelist
    -0.07
    recision
    -0.06
    plode
    -0.06
    isFunction
    -0.06
    abilité
    -0.06
    Russ
    -0.06
    POSITIVE LOGITS
     interest
    0.09
     attention
    0.08
    idy
    0.07
    attention
    0.07
    åĿĤ
    0.07
     curiosity
    0.07
     Interest
    0.07
    Interest
    0.07
     controversy
    0.06
    interest
    0.06
    Activations Density 0.023%

    No Known Activations