© 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. 82518
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to sustainability

    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
    czy
    -0.08
    zi
    -0.07
    son
    -0.07
    ëĿ½
    -0.07
    onder
    -0.06
    Locale
    -0.06
    cxx
    -0.06
    ample
    -0.06
     اÙĦÙħص
    -0.06
    annes
    -0.06
    POSITIVE LOGITS
    -minded
    0.10
     minded
    0.08
     credentials
    0.07
    istas
    0.07
    $MESS
    0.07
    /environment
    0.07
    -conscious
    0.07
    -energy
    0.07
     NR
    0.07
     quotient
    0.07
    Activations Density 0.006%

    No Known Activations