© 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. 125534
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedural or operational descriptions

    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
    eyse
    -0.08
    ccoli
    -0.08
    esel
    -0.08
    adx
    -0.07
    cé
    -0.07
     mesel
    -0.07
    olini
    -0.07
    olio
    -0.07
    loe
    -0.07
    ieux
    -0.07
    POSITIVE LOGITS
    uma
    0.06
    .Objects
    0.06
    Connections
    0.06
    as
    0.06
     relationships
    0.06
    dra
    0.06
     flow
    0.06
     Cy
    0.06
     qualitative
    0.06
     often
    0.06
    Activations Density 0.001%

    No Known Activations