© 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. 77416
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating location

    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
     Progressive
    -0.06
    anga
    -0.06
    abble
    -0.06
    vais
    -0.06
    bara
    -0.06
    389
    -0.06
    rai
    -0.06
    atomy
    -0.06
    mer
    -0.05
    ises
    -0.05
    POSITIVE LOGITS
    heel
    0.07
    æķ·
    0.07
    YRO
    0.07
    __$
    0.07
    uids
    0.07
     besides
    0.07
     ("-
    0.07
     corners
    0.07
    ülük
    0.07
    egin
    0.07
    Activations Density 0.026%

    No Known Activations