Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29062
    Prev
    Next
    INDEX
    Explanations

    section headers or category labels in a document

    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
     van
    -0.06
     Voll
    -0.06
    056
    -0.06
     Moo
    -0.06
    emo
    -0.06
     Doe
    -0.06
    opes
    -0.06
    amm
    -0.06
    itsu
    -0.06
     Tang
    -0.05
    POSITIVE LOGITS
    ç¯
    0.09
    .builders
    0.08
    elerik
    0.08
    akit
    0.08
     piger
    0.07
    é³
    0.07
    ÙĩÙĨ
    0.07
    kos
    0.07
    rawer
    0.07
    urum
    0.07
    Activations Density 0.000%

    No Known Activations