INDEX

Explanations

technical terminology and detailed descriptors related to scientific and engineering contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

isis

-0.15

æ¦

-0.15

oreach

-0.15

acid

-0.14

ERT

-0.14

 incident

-0.14

afs

-0.14

Fir

-0.14

Ú¯Ø§ÙĨ

-0.13

 inval

-0.13

POSITIVE LOGITS

others

0.16

phalt

0.16

abwe

0.14

HING

0.14

opard

0.14

adays

0.14

ÌĨ

0.14

lements

0.13

gregar

0.13

herits

0.13

Activations Density 0.223%

technical terminology and detailed descriptors related to scientific and engineering contexts

No Comments

No Known Activations