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. 1-LLAMASCOPE-RES-32K
    6. 23495
    Prev
    Next
    INDEX
    Explanations

    references to the concept of justice, specifically within the context of the criminal justice system and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izu
    -0.17
     misc
    -0.15
    ede
    -0.15
    ế
    -0.15
    inja
    -0.14
    ugi
    -0.14
    fty
    -0.14
     hardcore
    -0.13
     Harden
    -0.13
     Fold
    -0.13
    POSITIVE LOGITS
    essler
    0.18
    بار
    0.17
    ÑıÑħ
    0.16
    äch
    0.16
    cken
    0.15
    åĬ¨çĶŁæĪIJ
    0.15
    keit
    0.15
    ÐŁÐļ
    0.14
    peat
    0.14
    OOT
    0.14
    Activations Density 0.003%

    No Known Activations