© 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. 5-LLAMASCOPE-RES-131K
    11. 126140
    Prev
    Next
    INDEX
    Explanations

    terms related to classification or categorization

    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
    @js
    -0.07
    елÑİ
    -0.06
    à¥įà¤
    -0.06
    ð
    -0.06
    estre
    -0.06
    ноÑĪ
    -0.06
    ("__
    -0.06
    úsqueda
    -0.06
    ician
    -0.05
     Mour
    -0.05
    POSITIVE LOGITS
    ibre
    0.07
     Brend
    0.07
    eos
    0.07
    anford
    0.06
    rear
    0.06
    .localization
    0.06
    ea
    0.06
    iber
    0.06
    itan
    0.06
    eon
    0.06
    Activations Density 0.000%

    No Known Activations