INDEX

Explanations

instances of high frequency or notable occurrences in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

.lv

-0.16

èĶµ

-0.15

æª

-0.15

phia

-0.14

Î»Î¹Î¬

-0.14

elts

-0.14

AMESPACE

-0.14

 æĹ

-0.14

azzo

-0.14

endum

-0.14

POSITIVE LOGITS

0.17

rift

0.16

 divisible

0.15

 direction

0.15

0.14

 Carla

0.14

Activations Density 0.001%

instances of high frequency or notable occurrences in text

No Comments

No Known Activations