INDEX

Explanations

terms related to leadership positions and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

bak

-0.16

unga

-0.15

Bak

-0.15

 mess

-0.15

umble

-0.14

orget

-0.14

ijing

-0.14

uls

-0.14

amoto

-0.14

ation

-0.14

POSITIVE LOGITS

yor

0.18

erten

0.15

 defe

0.14

lor

0.14

Ð±ÐµÑĢ

0.13

ë¡

0.13

oric

0.13

ÙĪÙĨÛĮ

0.13

ÐµÑĢÑĪ

0.13

Activations Density 0.008%

terms related to leadership positions and roles

No Comments

No Known Activations