© 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. 17-LLAMASCOPE-RES-131K
    11. 56302
    Prev
    Next
    INDEX
    Explanations

    mentions of the internet and related online concepts

    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
    leases
    -0.06
     Hol
    -0.06
    ños
    -0.06
    обÑĢаÐ
    -0.06
    ucas
    -0.06
     Famil
    -0.06
    obbies
    -0.06
    chl
    -0.06
     hol
    -0.06
    enna
    -0.06
    POSITIVE LOGITS
    TouchUpInside
    0.07
    rost
    0.07
    isode
    0.07
    ADI
    0.07
    arges
    0.06
     resources
    0.06
    cae
    0.06
    licht
    0.06
    /print
    0.06
     leds
    0.06
    Activations Density 0.005%

    No Known Activations