© 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. 76300
    Prev
    Next
    INDEX
    Explanations

    references to coal and related materials

    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
    tems
    -0.07
    eworthy
    -0.06
    a
    -0.06
    ally
    -0.06
    nels
    -0.06
    ter
    -0.06
     Unit
    -0.06
    d
    -0.06
    eer
    -0.06
    ables
    -0.06
    POSITIVE LOGITS
    meal
    0.09
    обÑĢаÐ
    0.08
    walk
    0.08
    aceous
    0.07
    /pl
    0.07
    igi
    0.07
    workers
    0.07
    uckle
    0.07
    ickness
    0.07
    pool
    0.07
    Activations Density 0.026%

    No Known Activations