© 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. 103967
    Prev
    Next
    INDEX
    Explanations

    phrases related to concerns and policy discussions

    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
    estone
    -0.09
    ربÙĩ
    -0.08
    inia
    -0.07
    erne
    -0.07
    ãĥĪãĥ«
    -0.07
    ogn
    -0.07
    awning
    -0.07
    OKIE
    -0.07
    lete
    -0.07
     Fish
    -0.07
    POSITIVE LOGITS
     some
    0.07
     recent
    0.07
     certain
    0.07
     Certain
    0.06
    ogue
    0.06
    857
    0.06
    Some
    0.06
    æŁIJ
    0.06
     Some
    0.06
    Vault
    0.06
    Activations Density 0.034%

    No Known Activations