© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128476
    Prev
    Next
    INDEX
    Explanations

    implications and potential outcomes related to situations

    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
     Tape
    -0.07
    edic
    -0.06
     tape
    -0.06
     Frog
    -0.06
    ovies
    -0.05
    685
    -0.05
     following
    -0.05
    ive
    -0.05
    ighth
    -0.05
    ave
    -0.05
    POSITIVE LOGITS
     YOUR
    0.19
     yours
    0.17
    YOUR
    0.15
     your
    0.14
    your
    0.13
     ваÑĪ
    0.13
    ä½łçļĦ
    0.12
     YOU
    0.12
     votre
    0.11
     à¤Ĩपà¤ķ
    0.11
    Activations Density 0.043%

    No Known Activations