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. 95651
    Prev
    Next
    INDEX
    Explanations

    terms related to real estate and housing characteristics

    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
    tin
    -0.07
    ani
    -0.06
    946
    -0.06
    .levels
    -0.06
    ÑģÑĮого
    -0.06
    "user
    -0.06
    antis
    -0.06
    æ´ĭ
    -0.06
    ery
    -0.06
    (&$
    -0.06
    POSITIVE LOGITS
    chter
    0.08
    ellan
    0.07
     tay
    0.07
    onec
    0.07
    ovaly
    0.07
    oman
    0.06
    ãĥ³ãĥij
    0.06
    leine
    0.06
     car
    0.06
    enson
    0.06
    Activations Density 0.071%

    No Known Activations