INDEX

Explanations

identifiers and numeric data, likely related to research or technical details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Omn

-0.15

abbr

-0.15

acha

-0.15

 urban

-0.15

olia

-0.15

ddy

-0.15

 entitled

-0.14

 described

-0.14

iform

-0.14

POSITIVE LOGITS

bow

0.15

Ð°Ð»ÐµÐ¶

0.14

cpy

0.13

Î³Î·

0.13

.handleError

0.13

UILDER

0.13

.getProperties

0.13

ysa

0.13

urement

0.13

ifter

0.13

Activations Density 0.007%

identifiers and numeric data, likely related to research or technical details

No Comments

No Known Activations