© 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. 76925
    Prev
    Next
    INDEX
    Explanations

    instructions related to account access and enrollment processes

    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
     orig
    -0.06
    GLOBALS
    -0.06
    anki
    -0.06
     Transit
    -0.06
     Pit
    -0.06
    ÑģÑĭ
    -0.06
     Inbox
    -0.06
    åĢī
    -0.05
    hab
    -0.05
    iph
    -0.05
    POSITIVE LOGITS
    Speech
    0.08
    esis
    0.07
     parents
    0.07
    parents
    0.07
     spectator
    0.07
    #
    0.07
    Parents
    0.07
     parent
    0.07
    ",-
    0.07
    ÛĮرÙĩ
    0.07
    Activations Density 0.037%

    No Known Activations