© 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. 22-LLAMASCOPE-RES-131K
    11. 3635
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Lucy" in various contexts

    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
    £½
    -0.08
    edl
    -0.08
    atoon
    -0.08
    nila
    -0.07
    hti
    -0.07
    typeName
    -0.07
    ½
    -0.07
    ekler
    -0.07
    aval
    -0.07
    arie
    -0.07
    POSITIVE LOGITS
     Prot
    0.07
    dog
    0.07
    omba
    0.07
    olk
    0.07
    ÐĬ
    0.06
    inct
    0.06
     apprec
    0.06
     prot
    0.06
    g
    0.06
    bane
    0.06
    Activations Density 0.001%

    No Known Activations