INDEX

Explanations

codes and programming-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÎµÏģÎ³

-0.17

å¯º

-0.16

ewater

-0.15

.btnSave

-0.15

rve

-0.15

UNU

-0.14

iqueta

-0.14

gren

-0.14

svp

-0.14

.bid

-0.14

POSITIVE LOGITS

oned

0.18

uto

0.18

UTO

0.17

Wer

0.15

ongan

0.14

Wer

0.14

tl

0.14

 either

0.14

ties

0.14

eon

0.14

Activations Density 0.172%

codes and programming-related terms

No Comments

No Known Activations