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. 24-LLAMASCOPE-RES-32K
    6. 15499
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts related to real estate investment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anos
    -0.16
    rait
    -0.15
     ratings
    -0.15
    loff
    -0.15
    stakes
    -0.15
     spill
    -0.14
     Ratings
    -0.14
    unate
    -0.14
     æĺ¥
    -0.14
    ney
    -0.14
    POSITIVE LOGITS
     flips
    0.28
     flipped
    0.22
     flip
    0.22
    flip
    0.22
     flipping
    0.22
    Flip
    0.21
     rehab
    0.21
     Rehab
    0.21
     investor
    0.21
     Passive
    0.21
    Activations Density 0.054%

    No Known Activations