Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29217
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate an increase or demand for quality, quantity, or improvement

    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
     enough
    -0.07
     же
    -0.07
    /her
    -0.07
    oret
    -0.06
    aniel
    -0.06
     or
    -0.06
     etc
    -0.06
    ãĢħ
    -0.06
    ÚĨار
    -0.06
    jeme
    -0.06
    POSITIVE LOGITS
    .mybatisplus
    0.07
     sayıda
    0.07
    ayette
    0.07
    â̳
    0.07
    ounding
    0.07
    omor
    0.07
    934
    0.06
    uyen
    0.06
    Assignable
    0.06
    overs
    0.06
    Activations Density 0.036%

    No Known Activations