© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70917
    Prev
    Next
    INDEX
    Explanations

    concepts related to epidemiology and network theory

    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
     darker
    -0.07
    avern
    -0.06
     abuse
    -0.06
    iffe
    -0.06
     PyTuple
    -0.06
     plugs
    -0.06
     salvage
    -0.06
     asympt
    -0.06
    ullet
    -0.06
     Abuse
    -0.06
    POSITIVE LOGITS
    ritical
    0.07
    critical
    0.07
     critical
    0.07
     Critical
    0.07
    Critical
    0.07
    dob
    0.07
     disorder
    0.06
     Land
    0.06
     Hayward
    0.06
     thermal
    0.06
    Activations Density 0.060%

    No Known Activations