© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95899
    Prev
    Next
    INDEX
    Explanations

    terms related to economical and environmental concerns

    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
    awe
    -0.08
    vale
    -0.08
    ngth
    -0.07
    monds
    -0.07
    bulan
    -0.07
    arget
    -0.07
    apore
    -0.07
    ekli
    -0.07
    ForKey
    -0.07
    tep
    -0.07
    POSITIVE LOGITS
     ones
    0.10
     Ones
    0.07
     Banc
    0.07
    ActionCreators
    0.07
     Goldberg
    0.07
    ones
    0.06
     Ge
    0.06
     Weiner
    0.06
    olla
    0.06
    ÅĤem
    0.06
    Activations Density 0.025%

    No Known Activations