© 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. 76229
    Prev
    Next
    INDEX
    Explanations

    activities and amenities related to vacationing and sports

    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
    ,[],
    -0.07
    ente
    -0.07
    orum
    -0.07
    eway
    -0.07
     adverts
    -0.07
     fucking
    -0.06
    essler
    -0.06
     Maar
    -0.06
    lead
    -0.06
    ushima
    -0.06
    POSITIVE LOGITS
     заг
    0.07
    bcm
    0.07
    é§ħå¾ĴæŃ©
    0.06
    -plus
    0.06
     #-
    0.06
    eger
    0.06
     laisse
    0.06
    VIRTUAL
    0.06
    utter
    0.06
     Zak
    0.06
    Activations Density 0.005%

    No Known Activations