© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89754
    Prev
    Next
    INDEX
    Explanations

    real estate listings and property details

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ÑģÑĤа
    -0.06
     dow
    -0.06
     Trading
    -0.06
     sw
    -0.06
    adia
    -0.06
    reau
    -0.06
    _lineno
    -0.06
     Bush
    -0.06
     Roose
    -0.06
    amo
    -0.05
    POSITIVE LOGITS
    MLS
    0.08
    loor
    0.08
    بÙĪاسطة
    0.08
    apus
    0.07
    éĬ
    0.07
    avou
    0.07
     Agents
    0.07
     agent
    0.07
    TransparentColor
    0.07
     MLS
    0.06
    Activations Density 0.000%

    No Known Activations