© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61972
    Prev
    Next
    INDEX
    Explanations

    references to personal memories and experiences

    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
    Ả
    -0.07
    vens
    -0.07
    odem
    -0.06
    ypes
    -0.06
    είÏĦε
    -0.06
     Latest
    -0.06
    ActionCode
    -0.06
    adil
    -0.06
    umer
    -0.06
    ixel
    -0.06
    POSITIVE LOGITS
     how
    0.07
     another
    0.07
    unken
    0.06
    ovid
    0.06
     trouble
    0.06
     promise
    0.06
     earlier
    0.06
    vanished
    0.06
    rát
    0.06
     childhood
    0.06
    Activations Density 0.007%

    No Known Activations