© 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. 15-LLAMASCOPE-RES-131K
    11. 103701
    Prev
    Next
    INDEX
    Explanations

    phrases related to installation and technical requirements

    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
    udes
    -0.06
    abee
    -0.06
    cott
    -0.06
    mam
    -0.06
    ulta
    -0.06
    ettel
    -0.06
    ุà¹Ī
    -0.06
    té
    -0.06
    aes
    -0.06
     history
    -0.05
    POSITIVE LOGITS
    _bullet
    0.07
     forState
    0.07
    623
    0.07
    436
    0.07
    ³
    0.06
    TEGR
    0.06
     Guth
    0.06
    633
    0.06
    532
    0.06
    ByUrl
    0.06
    Activations Density 0.015%

    No Known Activations