© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 20860
    Prev
    Next
    INDEX
    Explanations

    phrases related to reiteration and vocal expression of thoughts or feelings

    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
    omi
    -0.16
    ä½ı
    -0.15
    ħĮ
    -0.15
    Invariant
    -0.14
    eck
    -0.14
    illisecond
    -0.14
    ëį°ìĿ´íĬ¸
    -0.14
    illet
    -0.14
    <context
    -0.14
    arp
    -0.14
    POSITIVE LOGITS
     publicly
    0.34
     loud
    0.26
     Loud
    0.25
     openly
    0.25
    .public
    0.24
     púb
    0.23
     public
    0.23
    åħ¬å¼Ģ
    0.22
     aloud
    0.22
    loud
    0.21
    Activations Density 0.231%

    No Known Activations