© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126506
    Prev
    Next
    INDEX
    Explanations

    the name "Edison" and its variations in context, particularly related to bankruptcy scenarios

    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
    ajar
    -0.07
    ung
    -0.06
    andard
    -0.06
    TEL
    -0.06
    -ever
    -0.06
    oriously
    -0.06
    intel
    -0.06
    è¡£
    -0.06
    (est
    -0.06
    enet
    -0.06
    POSITIVE LOGITS
    наÑĩе
    0.08
    nect
    0.07
    nu
    0.07
    arken
    0.07
    456
    0.07
    grams
    0.07
    ë¥ĺ
    0.07
    GRAM
    0.07
    ians
    0.06
    no
    0.06
    Activations Density 0.001%

    No Known Activations