INDEX

Explanations

terms related to measurement, quantities, and physical attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Crosby

-0.16

iceps

-0.15

ä¸ŃåŃ¦

-0.14

zsche

-0.13

pte

-0.13

 Grades

-0.13

ÏĩÏİ

-0.13

ENSE

-0.13

readcr

-0.13

aliz

-0.13

POSITIVE LOGITS

ig

0.93

ig

0.72

IG

0.72

Ig

0.71

Ð¸Ð³

0.69

ige

0.67

IG

0.66

iga

0.64

igs

0.61

igi

0.59

Activations Density 0.222%

terms related to measurement, quantities, and physical attributes

No Comments

No Known Activations