© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 103317
    Prev
    Next
    INDEX
    Explanations

    conjunctions and expressions of collaborative action

    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
     esk
    -0.08
    racat
    -0.08
    rát
    -0.08
    cak
    -0.08
    lád
    -0.08
    kem
    -0.07
    uario
    -0.07
    esk
    -0.07
    upe
    -0.07
    uu
    -0.07
    POSITIVE LOGITS
     instead
    0.10
    Instead
    0.10
     Instead
    0.10
    instead
    0.08
     вмеÑģÑĤ
    0.07
    onto
    0.07
     Hello
    0.06
     become
    0.06
     replaced
    0.06
    ib
    0.06
    Activations Density 0.023%

    No Known Activations