© 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. 105891
    Prev
    Next
    INDEX
    Explanations

    elements related to political events and investigations

    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
    ,[],
    -0.07
    neath
    -0.07
    Ðİ
    -0.06
    ouncill
    -0.06
     Neighbor
    -0.06
     amongst
    -0.06
    -âĢIJ
    -0.06
    .gnu
    -0.06
     POLITICO
    -0.06
    @[
    -0.06
    POSITIVE LOGITS
    quate
    0.07
    roit
    0.07
    å¾ĭ
    0.07
     nameof
    0.07
    ÅĪ
    0.06
    ktor
    0.06
     cud
    0.06
    sa
    0.06
    spm
    0.06
     emot
    0.06
    Activations Density 0.001%

    No Known Activations