INDEX

Explanations

numerical data and identifiers related to scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Moder

-0.18

awi

-0.17

Hoy

-0.16

 Moderator

-0.16

çĿ

-0.15

utral

-0.15

ad

-0.15

 Bravo

-0.14

 Rena

-0.14

 tangent

-0.14

POSITIVE LOGITS

%E

0.16

 æ¼

0.15

 meiden

0.15

IOUS

0.14

Ð¾Ð±ÑīÐµ

0.14

.gb

0.13

Å¡lo

0.13

kiye

0.13

	TokenName

0.13

.desktop

0.13

Activations Density 0.040%

numerical data and identifiers related to scientific research

No Comments

No Known Activations