INDEX

Explanations

HTML elements and tags related to website navigation or structure

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

ozor

-0.17

paragus

-0.16

apro

-0.15

abbo

-0.15

 sovere

-0.14

aan

-0.14

hide

-0.14

orable

-0.14

ATAB

-0.14

elm

-0.14

POSITIVE LOGITS

.experimental

0.15

 Eastern

0.15

 Maze

0.14

.Normalize

0.14

omens

0.13

ogn

0.13

vla

0.13

èĪĮ

0.13

 maps

0.13

lique

0.13

Activations Density 0.016%

HTML elements and tags related to website navigation or structure

No Comments

No Known Activations