© 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. 17-LLAMASCOPE-RES-131K
    6. 16273
    Prev
    Next
    INDEX
    Explanations

    actions and options for taking initiative

    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
    466
    -0.06
    iment
    -0.06
     Reform
    -0.06
    svp
    -0.06
    vale
    -0.06
    ioni
    -0.06
    458
    -0.06
    .Companion
    -0.06
    »¿
    -0.06
    idis
    -0.06
    POSITIVE LOGITS
    athi
    0.07
     Barcl
    0.07
    ica
    0.07
    chet
    0.06
    abb
    0.06
     francais
    0.06
    acomment
    0.06
    iglia
    0.06
    arges
    0.06
     miglior
    0.06
    Activations Density 0.011%

    No Known Activations