© 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. 8-LLAMASCOPE-RES-32K
    6. 6750
    Prev
    Next
    INDEX
    Explanations

    mentions of RSS feeds and related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atz
    -0.17
     fund
    -0.17
    edii
    -0.16
    ð
    -0.15
    edi
    -0.15
    ondon
    -0.15
    consts
    -0.14
    elf
    -0.14
    °
    -0.14
    ioneer
    -0.14
    POSITIVE LOGITS
     nackte
    0.16
    Advertisements
    0.16
    nip
    0.16
    /GPL
    0.16
    iston
    0.14
     Gib
    0.14
    \Collections
    0.14
    792
    0.14
    uhl
    0.13
    zcze
    0.13
    Activations Density 0.004%

    No Known Activations