© 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. 4-LLAMASCOPE-RES-32K
    11. 28636
    Prev
    Next
    INDEX
    Explanations

    instances of 'the' followed by different contextual elements, indicating a focus on specific subjects or themes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odzi
    -0.17
    amar
    -0.14
    teil
    -0.14
    versation
    -0.14
    ɵ
    -0.14
    chen
    -0.14
    SENS
    -0.14
    zia
    -0.14
     disproportion
    -0.13
    液
    -0.13
    POSITIVE LOGITS
     others
    0.24
    others
    0.19
     Others
    0.17
    ãģ£ãģ±
    0.17
    Others
    0.14
    VERR
    0.13
    AspNet
    0.13
    dbo
    0.13
    νοÏį
    0.13
    Locker
    0.13
    Activations Density 0.074%

    No Known Activations