INDEX

Explanations

code snippets or programming constructs related to parts or sections of software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

aska

-0.16

Ã¤

-0.15

ijk

-0.15

 bound

-0.15

/tos

-0.14

bound

-0.14

ematik

-0.14

ìĨĮ

-0.14

iven

-0.13

Ø§ÙģØ©

-0.13

POSITIVE LOGITS

.MouseAdapter

0.16

ndo

0.15

.sky

0.15

Moy

0.15

norm

0.14

çĶļ

0.14

oir

0.14

xon

0.14

istani

0.14

odied

0.13

Activations Density 0.090%

code snippets or programming constructs related to parts or sections of software

No Comments

No Known Activations