© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27307
    Prev
    Next
    INDEX
    Explanations

    mentions of technological advancements related to electronics and computing

    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
    aben
    -0.07
     fitte
    -0.07
    à¸ķร
    -0.06
    zug
    -0.06
    aurant
    -0.06
     Zar
    -0.06
     clone
    -0.06
     Sat
    -0.06
     Osama
    -0.06
    atem
    -0.06
    POSITIVE LOGITS
     demonstrations
    0.07
     Nature
    0.06
    bery
    0.06
    .twitch
    0.06
     deposited
    0.06
    Nature
    0.06
     demonstrators
    0.06
     lab
    0.06
     impr
    0.06
    iets
    0.06
    Activations Density 0.010%

    No Known Activations