INDEX

Explanations

words related to procedural instructions or data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ê

-0.17

è²¼

-0.15

.tell

-0.14

ATAR

-0.14

 Cheer

-0.14

 credible

-0.14

 dostan

-0.14

 Coff

-0.14

advertisement

-0.14

Å¾i

-0.13

POSITIVE LOGITS

 drill

0.15

hana

0.14

 fields

0.14

ãĥ³ãĥ

0.14

 mastered

0.14

child

0.14

 grop

0.14

 child

0.14

 FORCE

0.13

ook

0.13

Activations Density 0.188%

words related to procedural instructions or data management

No Comments

No Known Activations