INDEX

Explanations

specific formatting or style elements within textual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

/../

-0.16

BOVE

-0.15

IBUT

-0.15

otts

-0.14

 Sharma

-0.14

odore

-0.14

cplusplus

-0.14

lle

-0.13

sted

-0.13

INA

-0.13

POSITIVE LOGITS

ãĤ»ãĥ³ãĤ¿ãĥ¼

0.15

iglia

0.15

ichten

0.14

 ÙĨÙĪÙģ

0.13

Î±ÏģÎ±

0.13

CSI

0.13

.'/'.$

0.13

eyse

0.13

eyh

0.13

fram

0.12

Activations Density 0.043%

specific formatting or style elements within textual content

No Comments

No Known Activations