© 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. 889
    Prev
    Next
    INDEX
    Explanations

    segments of code or syntax structures in programming languages

    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
    наÑĤ
    -0.06
    ecast
    -0.06
    zek
    -0.06
     dum
    -0.06
    shr
    -0.06
     sadd
    -0.06
     att
    -0.05
    oshi
    -0.05
    abb
    -0.05
    bout
    -0.05
    POSITIVE LOGITS
    ç«
    0.07
    asher
    0.07
    ZA
    0.07
     Rencontre
    0.07
    .::
    0.07
     Oliv
    0.07
    ì²ł
    0.06
    -banner
    0.06
     Picker
    0.06
    isphere
    0.06
    Activations Density 0.004%

    No Known Activations