© 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. 985
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events

    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
    WebResponse
    -0.07
    Cb
    -0.07
    enga
    -0.06
     Clearance
    -0.06
     clearance
    -0.05
    972
    -0.05
     unusually
    -0.05
    agascar
    -0.05
     whence
    -0.05
    icip
    -0.05
    POSITIVE LOGITS
    imbus
    0.08
    éijij
    0.08
    μμ
    0.08
     poil
    0.07
    alker
    0.07
     поÑĤен
    0.07
    amo
    0.07
    ichel
    0.07
    indre
    0.07
    .clientX
    0.07
    Activations Density 0.024%

    No Known Activations