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. 118824
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    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
    hangi
    -0.09
     Emblem
    -0.07
    aes
    -0.07
     Erotik
    -0.07
    nev
    -0.07
    .si
    -0.07
    _compat
    -0.07
    utf
    -0.07
    /Branch
    -0.06
    /framework
    -0.06
    POSITIVE LOGITS
     mus
    0.06
    å±Ģ
    0.06
    ilda
    0.06
     Wind
    0.06
     Toy
    0.06
     mock
    0.06
     profess
    0.06
    works
    0.06
     Rut
    0.06
    RTL
    0.05
    Activations Density 0.000%

    No Known Activations