© 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. 40137
    Prev
    Next
    INDEX
    Explanations

    expressions of congratulations and commendation

    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
    Å¡il
    -0.07
    ÑĢез
    -0.06
     Declaration
    -0.06
    leen
    -0.06
    vana
    -0.06
    pled
    -0.06
    omba
    -0.06
    oka
    -0.06
    rss
    -0.06
    CompleteListener
    -0.06
    POSITIVE LOGITS
     deserved
    0.17
     deserving
    0.14
     deserve
    0.14
     deserves
    0.11
     undes
    0.09
     mer
    0.09
     earned
    0.09
     merit
    0.08
     reward
    0.07
    earned
    0.07
    Activations Density 0.037%

    No Known Activations