INDEX

Explanations

terms related to management or supervision in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ziej

-0.17

zej

-0.16

icher

-0.15

ëŁī

-0.14

ÙİØ£

-0.14

steller

-0.14

scribe

-0.13

Transmission

-0.13

hood

-0.13

Ki

-0.13

POSITIVE LOGITS

zia

0.16

 ding

0.14

CLUDING

0.14

artner

0.14

lew

0.14

wald

0.14

_corners

0.13

 Tato

0.13

ody

0.13

rost

0.13

Activations Density 0.017%

terms related to management or supervision in various contexts

No Comments

No Known Activations