INDEX

Explanations

references to chapters in texts or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÛĮÙĩ

-0.18

ut

-0.16

yat

-0.16

Ã§o

-0.16

gid

-0.14

fully

-0.14

uro

-0.14

_version

-0.14

ollen

-0.14

anno

-0.14

POSITIVE LOGITS

ize

0.21

IZE

0.19

-long

0.19

-length

0.18

hip

0.18

ed

0.17

azzi

0.17

wise

0.17

ized

0.17

ãĥ¬ãĥĥãĥĪ

0.17

Activations Density 0.012%

references to chapters in texts or documents

No Comments

No Known Activations