© 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. 128558
    Prev
    Next
    INDEX
    Explanations

    instances of posts or documents with a timestamp or reference

    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
    ulet
    -0.07
    784
    -0.07
    ventions
    -0.06
    che
    -0.06
    idos
    -0.06
    vention
    -0.06
     Bilder
    -0.06
    heritance
    -0.06
     Easter
    -0.06
    secret
    -0.06
    POSITIVE LOGITS
    /lic
    0.07
     Modified
    0.07
    SCAN
    0.06
    odyn
    0.06
     modified
    0.06
    .foundation
    0.06
    Modification
    0.06
     modification
    0.06
    plex
    0.06
    PLICIT
    0.06
    Activations Density 0.003%

    No Known Activations