© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 1-LLAMASCOPE-RES-32K
    6. 7270
    Prev
    Next
    INDEX
    Explanations

    the word "when" in various contexts, indicating a focus on temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cope
    -0.18
    krv
    -0.17
    TriState
    -0.17
    HEMA
    -0.16
    olumn
    -0.15
    rollo
    -0.14
    nga
    -0.14
    го
    -0.14
     Ear
    -0.14
    holm
    -0.13
    POSITIVE LOGITS
    iam
    0.16
    abouts
    0.15
    orf
    0.15
    soever
    0.15
    Ī
    0.15
    rit
    0.15
     finally
    0.15
    arming
    0.14
    -либо
    0.14
     Haram
    0.14
    Activations Density 0.127%

    No Known Activations