© 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. 28848
    Prev
    Next
    INDEX
    Explanations

    references to media and public figures discussing controversies

    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
    .scalablytyped
    -0.10
    ONA
    -0.10
    .fhir
    -0.08
     peÄį
    -0.08
    éijij
    -0.08
    -valu
    -0.08
    ÃŃna
    -0.08
    OTS
    -0.08
    .LayoutStyle
    -0.07
    Äįan
    -0.07
    POSITIVE LOGITS
     fellow
    0.07
     G
    0.07
     D
    0.06
     his
    0.06
     J
    0.06
    heck
    0.06
     B
    0.06
     on
    0.06
     himself
    0.06
     A
    0.06
    Activations Density 0.037%

    No Known Activations