INDEX

Explanations

variations of the word "be" and forms of the verb "to be" across different contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ten

-0.21

 eleven

-0.17

 tenth

-0.17

 thousands

-0.17

 eighth

-0.16

Hundreds

-0.15

inth

-0.15

 millions

-0.15

 ninth

-0.15

 twelve

-0.15

POSITIVE LOGITS

0.69

0.67

0.65

0.64

0.63

0.62

0.61

Activations Density 0.450%

variations of the word "be" and forms of the verb "to be" across different contexts

No Comments

No Known Activations