INDEX

Explanations

references to specific roles, entities, or structures in professional and academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

dam

-0.17

æ£Ĵ

-0.16

 transform

-0.16

 transcript

-0.14

Lem

-0.14

translate

-0.14

Uns

-0.14

resse

-0.14

 Maple

-0.14

shint

-0.14

POSITIVE LOGITS

æ®Ĭ

0.17

achuset

0.16

ÏĦÎ¹ÎºÎ¿

0.16

TestCategory

0.15

ãĥ³ãĥĳ

0.15

/TR

0.14

.fun

0.14

inho

0.14

xygen

0.14

Activations Density 0.387%

references to specific roles, entities, or structures in professional and academic contexts

No Comments

No Known Activations