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

    Neuronpedia

    Jacobian LensNEW
    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. 31-LLAMASCOPE-RES-32K
    11. 16279
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to measurements, comparisons, and scientific metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -1.14
    ,
    -1.08
     in
    -1.05
     and
    -1.04
     (
    -1.03
     a
    -1.02
     the
    -0.99
     to
    -0.96
     on
    -0.95
    .
    -0.94
    POSITIVE LOGITS
    GuidId
    0.50
    Intialized
    0.49
    UsageId
    0.49
    URLException
    0.48
    FilterWhere
    0.48
    GenerationStrategy
    0.47
     RuntimeObject
    0.47
    HeaderCode
    0.46
    UrlParser
    0.46
    RuntimeObject
    0.46
    Activations Density 0.007%

    No Known Activations