© 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. 93664
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "leave" and its variations related to abandonment or departure

    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
    ige
    -0.07
    osa
    -0.06
    pas
    -0.06
    SEP
    -0.06
     diff
    -0.06
    otti
    -0.06
    unas
    -0.06
     ìĨIJ
    -0.05
    eding
    -0.05
    isbury
    -0.05
    POSITIVE LOGITS
    agal
    0.07
     Horny
    0.07
    ANTE
    0.07
    ãĤĩãģĨ
    0.07
     Ordering
    0.07
    zik
    0.07
    akte
    0.07
    IGNED
    0.07
    ONTAL
    0.06
    ë¥
    0.06
    Activations Density 0.014%

    No Known Activations