INDEX

Explanations

numerical values related to quantities, durations, and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Äįer

-0.18

/mm

-0.18

owell

-0.16

-meter

-0.16

meter

-0.16

 Minute

-0.16

 kilomet

-0.15

Ngh

-0.15

minute

-0.15

ìĽĶë¶ĢíĦ°

-0.15

POSITIVE LOGITS

0.19

(!

0.19

(!

0.18

 pages

0.17

-s

0.16

#!

0.16

Âł

0.16

XL

0.16

 calories

0.15

Activations Density 0.292%

numerical values related to quantities, durations, and measurements

No Comments

No Known Activations