INDEX

Explanations

phrases related to setting and defining boundaries or parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dw

-0.15

ãģĤãĤĬ

-0.15

plural

-0.14

xn

-0.14

Com

-0.14

duc

-0.14

civ

-0.13

_ED

-0.13

ouver

-0.13

.edu

-0.13

POSITIVE LOGITS

tle

0.21

 aside

0.19

Î¸Î¿ÏĤ

0.17

ANDARD

0.16

zte

0.16

geber

0.16

-upper

0.15

 Aside

0.15

igh

0.15

Aside

0.15

Activations Density 0.051%

phrases related to setting and defining boundaries or parameters

No Comments

No Known Activations