INDEX

Explanations

sorting and filtering options for data organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ektor

-0.15

ex

-0.14

ictionary

-0.14

yonel

-0.14

 dign

-0.13

NotExist

-0.13

Ð¶Ðµ

-0.13

irectory

-0.13

inter

-0.13

URNS

-0.13

POSITIVE LOGITS

Reverse

0.22

reverse

0.20

 DESC

0.20

Descending

0.19

 reverse

0.18

 Reverse

0.18

.reverse

0.17

_reverse

0.17

Inverse

0.17

.Reverse

0.17

Activations Density 0.053%

sorting and filtering options for data organization

No Comments

No Known Activations