INDEX

Explanations

references to popular films, particularly within the "Star Wars" franchise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

/Branch

-0.15

/Internal

-0.14

/Set

-0.14

-Regular

-0.14

-President

-0.14

/String

-0.13

oload

-0.13

rame

-0.13

Ã¡s

-0.13

.INSTANCE

-0.13

POSITIVE LOGITS

DataGridViewTextBoxColumn

0.18

ToolStripMenuItem

0.18

brtc

0.16

iii

0.15

ANGLES

0.14

ãĥ³ãĥĨãĤ£

0.14

 Sloan

0.14

OA

0.13

''

0.13

ii

0.13

Activations Density 1.037%

references to popular films, particularly within the "Star Wars" franchise

No Comments

No Known Activations