INDEX

Explanations

terms related to corporate or business structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

hk

-0.15

 host

-0.14

 subsection

-0.14

 plan

-0.14

 Skinny

-0.14

 Morg

-0.14

ivery

-0.14

 Pearce

-0.14

ÙĲÙĬ

-0.14

ects

-0.13

POSITIVE LOGITS

ÑĨÐµÑĢ

0.15

è§Ħæ¨¡

0.14

oreach

0.14

ulp

0.14

 Exists

0.14

æĴŃ

0.14

0.13

alls

0.13

 ÑĤÐ¾Ð¿

0.13

.toolbox

0.13

Activations Density 0.170%

terms related to corporate or business structures

No Comments

No Known Activations