© 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. 29640
    Prev
    Next
    INDEX
    Explanations

    words related to measurement

    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
    до
    -0.07
    Ø®ÙĪ
    -0.07
     propName
    -0.07
    .va
    -0.06
    ãĤ¤ãĤ¯
    -0.06
    åį
    -0.06
    ttl
    -0.06
    gross
    -0.06
    exampleInput
    -0.06
    enburg
    -0.06
    POSITIVE LOGITS
    igy
    0.07
    abb
    0.06
    igi
    0.06
    amation
    0.06
     Neville
    0.06
    imal
    0.06
    heit
    0.06
    igr
    0.06
    onds
    0.06
    ond
    0.06
    Activations Density 0.000%

    No Known Activations