© 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. 25-LLAMASCOPE-RES-32K
    11. 18544
    Prev
    Next
    INDEX
    Explanations

    terms related to disruptions and their consequences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aban
    -0.14
    ariat
    -0.14
    etch
    -0.13
    ÏĥÏĦε
    -0.13
    izon
    -0.13
    athering
    -0.13
    eyed
    -0.13
    oref
    -0.13
    omor
    -0.13
    mos
    -0.13
    POSITIVE LOGITS
     caused
    0.52
     created
    0.41
     CAUSED
    0.40
     occasion
    0.36
     generated
    0.34
    occasion
    0.34
     produced
    0.34
    created
    0.34
     due
    0.33
     Created
    0.31
    Activations Density 0.612%

    No Known Activations