INDEX

Explanations

terms related to usage and their implications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

alian

-0.17

emo

-0.15

ubo

-0.15

outer

-0.15

.grp

-0.14

nds

-0.14

ilde

-0.14

lds

-0.14

Wen

-0.14

filesize

-0.14

POSITIVE LOGITS

abr

0.16

à¸¡à¸Ń

0.15

Ã¦re

0.15

coma

0.14

ango

0.14

andle

0.14

aÄŁÄ±

0.14

UCT

0.13

anzi

0.13

surf

0.13

Activations Density 0.043%

terms related to usage and their implications in various contexts

No Comments

No Known Activations