© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 19027
    Prev
    Next
    INDEX
    Explanations

    references to product specifications and features related to packaging and sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kola
    -0.15
    =>'
    -0.15
     scatter
    -0.14
    lassen
    -0.14
    anvas
    -0.14
     Tr
    -0.14
    adata
    -0.14
     minimal
    -0.14
    kas
    -0.14
     heavily
    -0.13
    POSITIVE LOGITS
    #ad
    0.19
    azen
    0.18
    éri
    0.17
    (pack
    0.16
     pack
    0.15
    .Networking
    0.15
    ready
    0.15
    grav
    0.15
    #ab
    0.15
    /pkg
    0.15
    Activations Density 0.040%

    No Known Activations