© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 59626
    Prev
    Next
    INDEX
    Explanations

    phrases indicating processes or steps in a workflow

    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
    lech
    -0.08
    akis
    -0.06
    okay
    -0.06
    insky
    -0.06
    ESH
    -0.06
    ész
    -0.06
     Imper
    -0.06
     imper
    -0.06
    lew
    -0.06
    dag
    -0.06
    POSITIVE LOGITS
     conception
    0.09
     inception
    0.07
    ephy
    0.07
     arrival
    0.07
     initial
    0.07
    oice
    0.07
    YLON
    0.07
    ìłij
    0.07
    ception
    0.07
     diagnosis
    0.07
    Activations Density 0.009%

    No Known Activations