© 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. 17-LLAMASCOPE-RES-131K
    11. 127544
    Prev
    Next
    INDEX
    Explanations

    references to online search functions or queries

    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
     Stein
    -0.06
    ple
    -0.06
    argo
    -0.06
    ãĤ¯ãĤ»
    -0.06
    rede
    -0.06
     Rum
    -0.05
     e
    -0.05
    hen
    -0.05
    æĹı
    -0.05
     Pick
    -0.05
    POSITIVE LOGITS
     matches
    0.08
    Matches
    0.08
    exact
    0.08
     match
    0.08
    FOUND
    0.08
    Match
    0.07
    _MATCH
    0.07
    еви
    0.07
     Exact
    0.07
     relevance
    0.07
    Activations Density 0.004%

    No Known Activations