© 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. 40754
    Prev
    Next
    INDEX
    Explanations

    terms related to overnight stays and accommodations

    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
    廳
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    balls
    -0.07
    229
    -0.06
    ponge
    -0.06
    phalt
    -0.06
    quent
    -0.06
    念
    -0.06
     Fighters
    -0.06
    ба
    -0.06
    POSITIVE LOGITS
    ed
    0.10
    ers
    0.09
    er
    0.08
    ing
    0.07
    aneously
    0.07
    uno
    0.07
    ÛĮ
    0.07
    ly
    0.06
    mar
    0.06
    aneous
    0.06
    Activations Density 0.004%

    No Known Activations