© 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. 3287
    Prev
    Next
    INDEX
    Explanations

    phrases related to the quality and effects of espresso and coffee

    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
    iete
    -0.08
    afil
    -0.08
    ards
    -0.07
    еÑı
    -0.07
    eken
    -0.07
    arten
    -0.07
    riot
    -0.07
     MyBase
    -0.07
     pÅĻik
    -0.06
    ystone
    -0.06
    POSITIVE LOGITS
     Peg
    0.07
     Chap
    0.06
     chap
    0.06
    IRD
    0.06
     McGu
    0.06
     ФедеÑĢалÑĮ
    0.06
    ND
    0.05
     screen
    0.05
     tre
    0.05
    stdarg
    0.05
    Activations Density 0.001%

    No Known Activations