© 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. 93636
    Prev
    Next
    INDEX
    Explanations

    phrases related to sharing or opening content in new windows or tabs

    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
    urdu
    -0.07
    otland
    -0.07
    astes
    -0.07
    terior
    -0.07
    shelf
    -0.07
     erotische
    -0.06
    tractor
    -0.06
    ledged
    -0.06
    avings
    -0.06
    eft
    -0.06
    POSITIVE LOGITS
    opens
    0.07
     Essen
    0.07
    ://
    0.06
     Ritch
    0.06
    CLUDING
    0.06
     opened
    0.06
    Opens
    0.06
     decre
    0.06
    guid
    0.06
     seventh
    0.06
    Activations Density 0.001%

    No Known Activations