Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95966
    Prev
    Next
    INDEX
    Explanations

    references to economic shortages and their associated impacts

    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
    è½®
    -0.07
     unload
    -0.07
     operated
    -0.06
    ndon
    -0.06
    linger
    -0.06
     Shotgun
    -0.06
    orean
    -0.06
    series
    -0.06
    éré
    -0.06
     equally
    -0.06
    POSITIVE LOGITS
    abies
    0.08
    lehem
    0.07
    ÑģÑıг
    0.06
     missed
    0.06
    eyer
    0.06
    thood
    0.06
    ccoli
    0.06
     CONSEQUENTIAL
    0.06
     Friendly
    0.06
     bundle
    0.06
    Activations Density 0.025%

    No Known Activations