© 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. 106797
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and assistance

    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
    etus
    -0.07
    quist
    -0.07
    oney
    -0.07
    roid
    -0.06
    isc
    -0.06
     proven
    -0.06
     lineNumber
    -0.06
    unate
    -0.06
    ronic
    -0.06
    ersive
    -0.06
    POSITIVE LOGITS
     helps
    0.07
     Helps
    0.07
     help
    0.07
    PIPE
    0.07
     answer
    0.07
     Answer
    0.06
     helped
    0.06
    Help
    0.06
    Answer
    0.06
    rien
    0.06
    Activations Density 0.004%

    No Known Activations