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. 96137
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing universality or common experiences

    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
    itarian
    -0.07
    íģ
    -0.06
    TEL
    -0.06
    cheon
    -0.06
    alytics
    -0.06
    иÑĦ
    -0.06
     Plate
    -0.06
    igar
    -0.06
    clusion
    -0.06
    олн
    -0.06
    POSITIVE LOGITS
    JNI
    0.07
    ANJI
    0.06
     Nie
    0.06
     else
    0.06
    oris
    0.06
    rong
    0.06
     distr
    0.06
    ayne
    0.06
     Happ
    0.06
    .connections
    0.06
    Activations Density 0.008%

    No Known Activations