© 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. 28-LLAMASCOPE-RES-32K
    6. 746
    Prev
    Next
    INDEX
    Explanations

    email domains and web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yan
    -0.15
    odel
    -0.15
     emailed
    -0.15
    otec
    -0.14
     rough
    -0.14
    Xã
    -0.14
     email
    -0.14
    prox
    -0.14
     Cres
    -0.14
    ä»®
    -0.14
    POSITIVE LOGITS
    .au
    0.32
    .uk
    0.23
    .za
    0.21
    .br
    0.21
    .scalablytyped
    0.21
    .mx
    0.20
    .sg
    0.20
    .tw
    0.19
    .nz
    0.19
     Subject
    0.18
    Activations Density 0.022%

    No Known Activations