© 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. 62225
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or transitions from one place to another

    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
     Protest
    -0.07
    ief
    -0.06
     Play
    -0.06
    etable
    -0.06
     Fre
    -0.06
    çĵ¶
    -0.05
     trivia
    -0.05
    Play
    -0.05
    751
    -0.05
    æŀ¶
    -0.05
    POSITIVE LOGITS
    (exit
    0.08
    .Exit
    0.08
     exit
    0.08
    exit
    0.08
     exiting
    0.07
     exited
    0.07
    icken
    0.07
     Exit
    0.07
    anz
    0.07
    _EXIT
    0.07
    Activations Density 0.017%

    No Known Activations