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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96001
    Prev
    Next
    INDEX
    Explanations

    words related to martial arts and physical movements

    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
    ãģŁãĤī
    -0.07
    VertexArray
    -0.06
    996
    -0.06
     abl
    -0.06
     omn
    -0.06
    omal
    -0.06
    rax
    -0.06
    istrovstvÃŃ
    -0.06
    ì¹´ì§Ģëħ¸
    -0.06
    946
    -0.06
    POSITIVE LOGITS
    ocup
    0.08
    lernen
    0.07
    (Unknown
    0.07
    rost
    0.07
    eri
    0.07
    naments
    0.07
    adem
    0.06
    iteDatabase
    0.06
    ogie
    0.06
    Fluid
    0.06
    Activations Density 0.003%

    No Known Activations