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. 96260
    Prev
    Next
    INDEX
    Explanations

    statistics and outcomes related to sports events

    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
    ç§Ģ
    -0.07
     注
    -0.06
    mdp
    -0.06
    mts
    -0.06
    utral
    -0.06
    atables
    -0.06
    apg
    -0.06
    anche
    -0.06
    inge
    -0.06
    AYOUT
    -0.06
    POSITIVE LOGITS
     Burnett
    0.07
    reh
    0.06
    iera
    0.06
     astore
    0.06
    spy
    0.06
    999
    0.06
    adam
    0.06
    \uc
    0.06
     Erect
    0.06
     Cells
    0.06
    Activations Density 0.006%

    No Known Activations