© 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. 15-LLAMASCOPE-RES-131K
    6. 27209
    Prev
    Next
    INDEX
    Explanations

    instances of temporal or conditional phrases

    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
    indo
    -0.06
    enerator
    -0.06
     indeed
    -0.06
     btw
    -0.06
     Meaning
    -0.06
     Aires
    -0.05
    413
    -0.05
     yet
    -0.05
    ires
    -0.05
    berger
    -0.05
    POSITIVE LOGITS
    ÙĮ
    0.07
    /***/
    0.07
    èĮĥ
    0.07
    krv
    0.07
    _fsm
    0.07
    trl
    0.07
    CJK
    0.07
     Ãľl
    0.07
    ãĥ¶
    0.07
    تاÙĨ
    0.07
    Activations Density 0.059%

    No Known Activations