© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89938
    Prev
    Next
    INDEX
    Explanations

    causal relationships and explanations related to environmental issues

    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
    á»ħ
    -0.07
    .react
    -0.07
    oplan
    -0.07
    à¸Ńà¸ŀ
    -0.07
    il
    -0.07
    CLUDING
    -0.06
    -License
    -0.06
    æ
    -0.06
    kou
    -0.06
    redirectTo
    -0.06
    POSITIVE LOGITS
     reasons
    0.08
     lack
    0.07
     Gather
    0.07
    vik
    0.07
    akis
    0.07
     reason
    0.06
     sake
    0.06
     infl
    0.06
    stå
    0.06
    bid
    0.06
    Activations Density 0.018%

    No Known Activations