© 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. 29-LLAMASCOPE-RES-32K
    6. 2962
    Prev
    Next
    INDEX
    Explanations

    phrases related to marketing performance and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McInt
    -0.16
    μάÏĦÏīν
    -0.15
     McGregor
    -0.15
     meshes
    -0.15
     mosaic
    -0.15
    marsh
    -0.15
     Mata
    -0.15
     McGr
    -0.15
     Mandal
    -0.15
    ManagedObject
    -0.15
    POSITIVE LOGITS
     mil
    1.25
     Mil
    1.25
    Mil
    1.19
     Mill
    1.13
    mil
    1.12
     MIL
    1.11
     mill
    1.09
    Mill
    0.96
     mills
    0.95
    mill
    0.94
    Activations Density 0.240%

    No Known Activations