INDEX

Explanations

phrases related to definitions or explanations of terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

.shtml

-0.17

jab

-0.16

 Eisen

-0.15

abeth

-0.15

isa

-0.15

reich

-0.15

à¸Ļà¸Ħ

-0.14

lland

-0.14

 reversing

-0.14

POSITIVE LOGITS

 strict

0.15

strict

0.15

.dp

0.14

ishi

0.14

abble

0.14

 anlamda

0.14

urname

0.14

aller

0.14

ingleton

0.14

 leaked

0.13

Activations Density 0.096%

phrases related to definitions or explanations of terms and concepts

No Comments

No Known Activations