INDEX

Explanations

frequent and significant words or phrases that convey essential concepts in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.scalablytyped

-0.16

áº¡n

-0.15

RowAt

-0.14

swer

-0.14

mares

-0.14

stup

-0.14

 Bliss

-0.13

 ãĢľ

-0.13

(VALUE

-0.13

adoop

-0.13

POSITIVE LOGITS

dek

0.16

 Rudd

0.14

ern

0.14

onda

0.14

BST

0.14

vt

0.13

geist

0.13

BIO

0.13

osten

0.13

 pioneer

0.13

Activations Density 0.001%

frequent and significant words or phrases that convey essential concepts in the text

No Comments

No Known Activations