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. 18-LLAMASCOPE-RES-32K
    6. 2482
    Prev
    Next
    INDEX
    Explanations

    exclamatory or attention-grabbing phrases and events in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çIJ³
    -0.15
    ucha
    -0.15
    ãĥªãĥ³ãĤ°
    -0.15
    rias
    -0.14
    /welcome
    -0.14
    wers
    -0.14
    amoto
    -0.14
    wart
    -0.14
    <decltype
    -0.14
    ASE
    -0.14
    POSITIVE LOGITS
     recently
    0.31
    Recently
    0.26
     Recently
    0.25
     last
    0.20
     during
    0.20
     lately
    0.19
    recent
    0.19
     During
    0.18
    esterday
    0.18
     recent
    0.18
    Activations Density 0.409%

    No Known Activations