INDEX

Explanations

references to technical specifications and system configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãĥ¼ãĤ¹ãĥĪ

-0.16

Ð¾ÑĢÐµ

-0.16

udge

-0.15

 Ð¡ÑĥÐ´

-0.15

adding

-0.15

ahy

-0.15

áº¡c

-0.15

utherland

-0.15

eme

-0.14

aukee

-0.14

POSITIVE LOGITS

 switch

0.31

 Switch

0.28

-switch

0.27

switch

0.27

_switch

0.27

 switching

0.27

Switch

0.27

 replace

0.26

 replaced

0.26

 SWITCH

0.26

Activations Density 0.160%

references to technical specifications and system configurations

No Comments

No Known Activations