© 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. 90267
    Prev
    Next
    INDEX
    Explanations

    terms related to education and training programs

    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
     rob
    -0.06
    ein
    -0.06
    [$_
    -0.06
    ebi
    -0.06
    lict
    -0.06
     Insider
    -0.06
    -properties
    -0.06
    oy
    -0.06
     inversion
    -0.06
    ahlen
    -0.06
    POSITIVE LOGITS
    åŁº
    0.07
     nabÃŃd
    0.07
    .cls
    0.07
    dna
    0.07
    änd
    0.07
    WithPath
    0.07
     Pearson
    0.06
    ên
    0.06
    ymb
    0.06
    cke
    0.06
    Activations Density 0.002%

    No Known Activations