INDEX

Explanations

references to published works, particularly books and their 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

ansi

-0.19

Ĥ

-0.15

orable

-0.14

-:-

-0.14

iros

-0.14

lay

-0.14

olare

-0.14

inary

-0.13

ialog

-0.13

Bak

-0.13

POSITIVE LOGITS

oggle

0.17

à¸´à¸Ļà¸Ħ

0.16

ERRU

0.16

odon

0.16

ingo

0.16

ÃŃÅ¾

0.15

 Hutch

0.14

'gc

0.14

Ð²Ð¾Ð´

0.14

 kijken

0.14

Activations Density 0.203%

references to published works, particularly books and their details

No Comments

No Known Activations