© 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. 118183
    Prev
    Next
    INDEX
    Explanations

    collaborative efforts and partnerships among organizations

    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
     itself
    -0.08
    isay
    -0.07
    åıĬåħ¶
    -0.07
    abra
    -0.06
    jal
    -0.06
    Expose
    -0.06
    è¾ħ
    -0.06
    ieber
    -0.06
    ÑĩеÑģÑĤва
    -0.06
    Ñĸз
    -0.06
    POSITIVE LOGITS
     alike
    0.15
     together
    0.14
    joint
    0.13
     joint
    0.13
     Together
    0.12
    åħ±åIJĮ
    0.12
     partnership
    0.11
     respectively
    0.11
     jointly
    0.11
    Together
    0.11
    Activations Density 0.037%

    No Known Activations