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. 95977
    Prev
    Next
    INDEX
    Explanations

    references to World War II events and entities, particularly related to Britain

    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
    Ñĸб
    -0.07
    gewater
    -0.07
    oose
    -0.07
    ocz
    -0.07
     DISCLAIMS
    -0.07
    isos
    -0.07
    bedo
    -0.07
    دار
    -0.07
    emma
    -0.07
    yz
    -0.07
    POSITIVE LOGITS
    enido
    0.06
    660
    0.06
     Succ
    0.06
    Cit
    0.05
    itness
    0.05
    879
    0.05
     Mot
    0.05
     silent
    0.05
     Lex
    0.05
     Merrill
    0.05
    Activations Density 0.004%

    No Known Activations