© 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. 104398
    Prev
    Next
    INDEX
    Explanations

    discussion about app usage and privacy concerns

    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
     âĹĦ
    -0.07
    VertexArray
    -0.07
    озна
    -0.06
    ertz
    -0.06
    ntl
    -0.06
    plorer
    -0.06
    Û²Û°Û²
    -0.06
    burger
    -0.06
    _year
    -0.06
     Burl
    -0.06
    POSITIVE LOGITS
     sudden
    0.07
     following
    0.06
    onis
    0.06
    Impossible
    0.06
    irect
    0.06
     Surge
    0.06
     suddenly
    0.06
     spike
    0.06
    Forget
    0.06
     days
    0.06
    Activations Density 0.008%

    No Known Activations