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. 21-LLAMASCOPE-RES-32K
    6. 8731
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to government and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rig
    -0.19
    rone
    -0.19
    odb
    -0.18
    angelo
    -0.18
    isses
    -0.17
    rung
    -0.17
    ettle
    -0.17
    ett
    -0.16
    ring
    -0.16
    riger
    -0.15
    POSITIVE LOGITS
    ourmet
    0.19
    lat
    0.16
    ested
    0.16
    OLF
    0.15
    hee
    0.15
    azi
    0.15
    reetings
    0.15
    ût
    0.15
    KV
    0.15
    heard
    0.14
    Activations Density 0.041%

    No Known Activations