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. 95980
    Prev
    Next
    INDEX
    Explanations

    mentions of power or influence attributed to various entities or organizations

    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
    boro
    -0.07
    äd
    -0.07
    ä½į
    -0.07
    ignum
    -0.07
    icator
    -0.07
    borg
    -0.07
    olta
    -0.07
    adders
    -0.07
    ebi
    -0.07
    ureka
    -0.06
    POSITIVE LOGITS
    CHA
    0.08
     rij
    0.06
     Met
    0.06
    ystack
    0.06
    fully
    0.06
     Clar
    0.06
     Salv
    0.06
    zoom
    0.06
     Col
    0.06
     mole
    0.06
    Activations Density 0.003%

    No Known Activations