© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 369
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to housing and homelessness issues

    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
    emas
    -0.07
    velte
    -0.06
     duty
    -0.06
    AspectRatio
    -0.06
     paralysis
    -0.06
    ières
    -0.06
    æľį
    -0.06
     reinforcement
    -0.05
    pras
    -0.05
    adin
    -0.05
    POSITIVE LOGITS
     homeless
    0.10
     homelessness
    0.10
    usta
    0.09
    osti
    0.09
    oksen
    0.08
    iverz
    0.08
     Housing
    0.08
    .tap
    0.07
    CallCheck
    0.07
     ìĭ±ê¸Ģ
    0.07
    Activations Density 0.010%

    No Known Activations