Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 5412
    Prev
    Next
    INDEX
    Explanations

    words related to rejuvenation or renewal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    658
    -0.17
    mez
    -0.16
    ppard
    -0.15
    erman
    -0.15
    .deserialize
    -0.14
     MÃľ
    -0.14
    atoire
    -0.14
    retch
    -0.14
    INU
    -0.14
    987
    -0.14
    POSITIVE LOGITS
    .EventQueue
    0.16
    éĮ
    0.16
    Deployment
    0.14
    icont
    0.14
    XD
    0.14
    shal
    0.14
    irie
    0.14
    caff
    0.13
    .jquery
    0.13
    deployment
    0.13
    Activations Density 0.056%

    No Known Activations