© 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. 60078
    Prev
    Next
    INDEX
    Explanations

    PHP syntax and structure within code

    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
    arra
    -0.07
    byt
    -0.07
    pty
    -0.07
    AnimationFrame
    -0.07
    agini
    -0.06
    Thunk
    -0.06
     seins
    -0.06
    коз
    -0.06
    ÂŃs
    -0.06
     kims
    -0.06
    POSITIVE LOGITS
     McCl
    0.07
    ©
    0.06
    ष
    0.06
     Boyle
    0.06
    uur
    0.06
    tle
    0.06
    .DialogResult
    0.06
    ocos
    0.06
     key
    0.06
    Ïģία
    0.05
    Activations Density 0.001%

    No Known Activations