© 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. 17-LLAMASCOPE-RES-131K
    11. 119101
    Prev
    Next
    INDEX
    Explanations

    numerical values related to voting or scores

    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
    tal
    -0.07
    amework
    -0.06
     BATCH
    -0.06
     batch
    -0.06
     wall
    -0.06
     gall
    -0.06
    åįĵ
    -0.06
    uble
    -0.06
     vo
    -0.06
    umont
    -0.06
    POSITIVE LOGITS
    Ø°
    0.07
    алÑĮ
    0.07
     ancest
    0.06
    _INTERVAL
    0.06
     Abdel
    0.06
    кÑĸн
    0.06
    âij
    0.06
    .ActionListener
    0.06
     thôi
    0.06
    itan
    0.06
    Activations Density 0.000%

    No Known Activations