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. 125649
    Prev
    Next
    INDEX
    Explanations

    phrases that connect to popular culture or notable events in media

    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
    asmus
    -0.07
    imiter
    -0.07
    ughs
    -0.07
    atak
    -0.07
     
    -0.06
    ushman
    -0.06
     com
    -0.06
     de
    -0.06
    porte
    -0.06
     re
    -0.06
    POSITIVE LOGITS
    aset
    0.08
    าà¸ĩ
    0.07
    åĸĬ
    0.07
    INF
    0.07
    PED
    0.07
    Ñıб
    0.06
     threaded
    0.06
    Âłro
    0.06
    .tie
    0.06
    anders
    0.06
    Activations Density 0.021%

    No Known Activations