INDEX

Explanations

references to teaching and learning contexts

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

uki

-0.18

chop

-0.16

á»ĩn

-0.15

leton

-0.15

 Leban

-0.14

ardi

-0.14

ç¶Ń

-0.14

iams

-0.14

TOT

-0.14

clare

-0.14

POSITIVE LOGITS

 Noon

0.15

zl

0.15

bao

0.14

 Muss

0.14

ppo

0.14

 Baths

0.14

itas

0.14

/front

0.14

Ø´Ø¯

0.14

ythe

0.14

Activations Density 0.777%

references to teaching and learning contexts

No Comments

No Known Activations