© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84099
    Prev
    Next
    INDEX
    Explanations

    references to apostles and the concept of apostolic authority or faith

    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
    ãĥ¼ãĤ¯
    -0.08
    atta
    -0.07
    ikut
    -0.07
    ifax
    -0.07
    xes
    -0.07
    istica
    -0.07
    uxtap
    -0.06
    aby
    -0.06
    ÑĤоÑĩ
    -0.06
    awah
    -0.06
    POSITIVE LOGITS
    ures
    0.08
    ries
    0.07
    regon
    0.07
    ria
    0.07
    ion
    0.07
    -ap
    0.07
    eos
    0.07
    legate
    0.06
    rello
    0.06
    les
    0.06
    Activations Density 0.002%

    No Known Activations