INDEX

Explanations

punctuations and specific technical terminology related to file formats and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ocz

-0.16

ooks

-0.16

Jed

-0.15

reme

-0.15

alley

-0.15

Ã©r

-0.15

ÄĻ

-0.14

å¯©

-0.14

¤íĶĦ

-0.14

POSITIVE LOGITS

tri

0.15

_DISABLE

0.15

pus

0.14

tri

0.14

ctal

0.13

 Sharp

0.13

rious

0.13

blings

0.13

child

0.13

 Shared

0.13

Activations Density 0.358%

punctuations and specific technical terminology related to file formats and data processing

No Comments

No Known Activations