Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4777
    Prev
    Next
    INDEX
    Explanations

    terms related to controversy and disputes

    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
    ulin
    -0.10
    itude
    -0.09
    nie
    -0.08
    ALLERY
    -0.08
    rone
    -0.07
    .contentMode
    -0.07
    ery
    -0.07
    -bodied
    -0.07
    /watch
    -0.07
    erg
    -0.07
    POSITIVE LOGITS
     surrounding
    0.09
     Surround
    0.08
     about
    0.08
     over
    0.08
     surround
    0.07
    /error
    0.07
    ously
    0.07
    404
    0.06
     generated
    0.06
    rary
    0.06
    Activations Density 0.003%

    No Known Activations