© 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. 15-LLAMASCOPE-RES-131K
    11. 26939
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional statements and justifications

    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
    ral
    -0.06
     strict
    -0.06
     Sr
    -0.05
     Mir
    -0.05
    iasi
    -0.05
    urette
    -0.05
     Ein
    -0.05
    avan
    -0.05
    çĿ£
    -0.05
     VAN
    -0.05
    POSITIVE LOGITS
    opak
    0.08
    reasonable
    0.07
    iets
    0.07
    GINE
    0.07
    èįī
    0.07
    isContained
    0.07
    ignum
    0.07
    iena
    0.06
    matchCondition
    0.06
    Fuse
    0.06
    Activations Density 0.021%

    No Known Activations