© 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. 119189
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the state or condition of items or people related to features or attributes

    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
    rien
    -0.07
    kup
    -0.07
    ryn
    -0.07
    ekl
    -0.07
    ncmp
    -0.06
    ifo
    -0.06
    abb
    -0.06
    ambda
    -0.06
    خصÙĪص
    -0.06
    太éĥİ
    -0.06
    POSITIVE LOGITS
     added
    0.08
    outh
    0.08
     only
    0.07
    ouri
    0.07
    ória
    0.07
    aida
    0.07
    ruba
    0.07
    ılım
    0.06
     #__
    0.06
    otu
    0.06
    Activations Density 0.030%

    No Known Activations