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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-LLAMASCOPE-RES-32K
    6. 28385
    Prev
    Next
    INDEX
    Explanations

    topics related to safety, environmental, and health-related organizations or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lod
    -0.16
    akan
    -0.15
    avia
    -0.15
    vir
    -0.15
    éĹ´
    -0.14
    rrha
    -0.14
    asm
    -0.14
    iph
    -0.14
    ORY
    -0.13
    va
    -0.13
    POSITIVE LOGITS
    еÑĢп
    0.15
    (NS
    0.14
    _IMPLEMENT
    0.14
    rox
    0.14
    _Tis
    0.14
    itespace
    0.14
    mos
    0.14
    iri
    0.13
     apart
    0.13
    _FINE
    0.13
    Activations Density 0.050%

    No Known Activations