© 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. 125479
    Prev
    Next
    INDEX
    Explanations

    processes and actions related to production and improvement

    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
    .TestTools
    -0.08
    егоÑĢ
    -0.07
    Ìģt
    -0.07
    jmp
    -0.07
    esimal
    -0.07
     Koch
    -0.07
    olan
    -0.07
     znam
    -0.07
    _INCREMENT
    -0.06
    .af
    -0.06
    POSITIVE LOGITS
     process
    0.14
    process
    0.12
    è¿ĩç¨ĭ
    0.11
    _process
    0.10
     Process
    0.10
    Process
    0.10
     processo
    0.09
     proces
    0.09
     пÑĢоÑĨеÑģÑģ
    0.09
    -process
    0.08
    Activations Density 0.034%

    No Known Activations