© 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. 15-LLAMASCOPE-RES-131K
    11. 90006
    Prev
    Next
    INDEX
    Explanations

    specific nouns and actions related to winning and achievement

    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
    опÑĢи
    -0.07
    bru
    -0.07
    idi
    -0.07
    lett
    -0.07
    ãĥ³ãĥģ
    -0.07
    older
    -0.07
    airo
    -0.07
    leri
    -0.06
     Åŀah
    -0.06
    edd
    -0.06
    POSITIVE LOGITS
     with
    0.17
    with
    0.13
     vỼi
    0.13
    _with
    0.11
     avec
    0.11
     dengan
    0.11
     With
    0.10
     WITH
    0.10
    	with
    0.10
    -with
    0.09
    Activations Density 0.026%

    No Known Activations