© 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. 76858
    Prev
    Next
    INDEX
    Explanations

    keywords related to geographical locations or places

    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
    isas
    -0.06
    zsche
    -0.06
    POSIT
    -0.06
    oulos
    -0.06
    utter
    -0.06
    ìĦĿ
    -0.06
     Cem
    -0.06
    uber
    -0.06
    leon
    -0.06
    ãĥĥãĥĦ
    -0.06
    POSITIVE LOGITS
    ruk
    0.07
    оÑĢоÑĤ
    0.06
    /dc
    0.06
     unreasonable
    0.06
    oro
    0.06
    afa
    0.06
    mars
    0.06
    rier
    0.06
    fest
    0.06
     ê°ģ
    0.06
    Activations Density 0.000%

    No Known Activations