© 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. 56266
    Prev
    Next
    INDEX
    Explanations

    themes of individual growth and emotional connections

    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
    erin
    -0.08
    ollar
    -0.06
    ì§ĢëĬĶ
    -0.06
    ç¦ıåĪ©
    -0.06
    vern
    -0.06
    à¥ģà¤
    -0.06
    æ¦Ĥ
    -0.06
     eser
    -0.06
    /proto
    -0.06
    oola
    -0.06
    POSITIVE LOGITS
     that
    0.09
    that
    0.08
    BCM
    0.07
    aket
    0.07
    upal
    0.06
    utoff
    0.06
    ãģĮ
    0.06
     että
    0.06
    /REC
    0.06
     že
    0.06
    Activations Density 0.051%

    No Known Activations