© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126023
    Prev
    Next
    INDEX
    Explanations

    references to collaborating entities and initiatives, particularly in the context of governance and international relations

    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
     remember
    -0.06
     our
    -0.06
     a
    -0.06
     #
    -0.06
     and
    -0.06
     NO
    -0.06
     hang
    -0.06
    .
    -0.06
     aren
    -0.06
    ,
    -0.06
    POSITIVE LOGITS
    ycastle
    0.09
    izont
    0.09
    .volley
    0.08
    ÑĪиб
    0.08
     paci
    0.08
    ÑĥÑĩа
    0.08
    одо
    0.08
    á»ĵ
    0.08
    orners
    0.08
    zeit
    0.08
    Activations Density 0.000%

    No Known Activations