© 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. 126259
    Prev
    Next
    INDEX
    Explanations

    references to sending mail configurations and processes

    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
    illery
    -0.07
    edes
    -0.07
    usp
    -0.07
    -пÑĢав
    -0.06
    xon
    -0.06
    inn
    -0.06
    endas
    -0.06
    ycin
    -0.06
    ching
    -0.06
    818
    -0.06
    POSITIVE LOGITS
    ril
    0.09
    ings
    0.09
    encer
    0.08
    illance
    0.08
    bote
    0.07
    ables
    0.07
    etermine
    0.07
    ancement
    0.07
    zcze
    0.07
    ers
    0.07
    Activations Density 0.011%

    No Known Activations