© 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. 75225
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate attention or observation

    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
    lya
    -0.07
     Plug
    -0.07
     strict
    -0.06
    Plug
    -0.06
     è«
    -0.06
    BITS
    -0.06
    Backing
    -0.06
    ilos
    -0.06
     plug
    -0.06
    orian
    -0.06
    POSITIVE LOGITS
     closely
    0.09
     nam
    0.07
    nex
    0.07
    ActionCreators
    0.07
    ainen
    0.07
    braco
    0.06
     ReSharper
    0.06
     future
    0.06
    UBL
    0.06
    PropTypes
    0.06
    Activations Density 0.004%

    No Known Activations