INDEX

Explanations

sections and references within a structured document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ertino

-0.15

ety

-0.15

vod

-0.14

hora

-0.14

/meta

-0.14

WidgetItem

-0.14

iks

-0.14

.operator

-0.14

uur

-0.14

ê¶ģ

-0.14

POSITIVE LOGITS

rimon

0.15

pill

0.14

lucent

0.14

ILLS

0.14

 Fernandez

0.13

itus

0.13

 Globals

0.13

 cases

0.13

Activations Density 0.400%

sections and references within a structured document

No Comments

No Known Activations