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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 12520
    Prev
    Next
    INDEX
    Explanations

    references to legal and governmental actions pertaining to public safety and health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BYU
    -0.17
    ControlEvents
    -0.17
     Opr
    -0.16
     Uint
    -0.15
    ãĥĥãĥģ
    -0.15
    reon
    -0.15
     KL
    -0.15
    uibModal
    -0.15
    /GPL
    -0.15
    KL
    -0.15
    POSITIVE LOGITS
     NJ
    0.69
    NJ
    0.61
     Jersey
    0.58
     Rutgers
    0.52
     nj
    0.51
     Newark
    0.50
    nj
    0.47
     Bergen
    0.46
     jersey
    0.39
     Trent
    0.35
    Activations Density 0.306%

    No Known Activations