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. 9-LLAMASCOPE-RES-131K
    6. 96122
    Prev
    Next
    INDEX
    Explanations

    components and history related to educational institutions

    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
     Amph
    -0.06
    anson
    -0.06
    yny
    -0.06
    igu
    -0.06
    inding
    -0.06
    eration
    -0.06
     Fib
    -0.06
    eka
    -0.05
    ifo
    -0.05
    omething
    -0.05
    POSITIVE LOGITS
    unto
    0.08
    onga
    0.07
    ãĥĪãĥ«
    0.07
    Disposable
    0.07
     asi
    0.06
    UNS
    0.06
    Ñħи
    0.06
    UILTIN
    0.06
    527
    0.06
    ä»ĬæĹ¥
    0.06
    Activations Density 0.008%

    No Known Activations