© 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. 17-LLAMASCOPE-RES-131K
    11. 126237
    Prev
    Next
    INDEX
    Explanations

    instances of rarity or uniqueness in various contexts

    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
    ÑĤаб
    -0.07
    isko
    -0.07
    ']!='
    -0.06
    chod
    -0.06
    prung
    -0.06
    pline
    -0.06
    aar
    -0.06
    rac
    -0.06
    ÑĦÑĢа
    -0.06
    retch
    -0.06
    POSITIVE LOGITS
    faction
    0.11
    -earth
    0.09
     occasions
    0.08
    Rare
    0.08
     occasion
    0.08
    ãĤ±ãĥ¼ãĤ¹
    0.07
     glimps
    0.07
    ily
    0.07
    urette
    0.07
    f
    0.07
    Activations Density 0.020%

    No Known Activations