INDEX

Explanations

elements related to specific institutions and their functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ìļ´

-0.15

èį

-0.14

emouth

-0.14

 addCriterion

-0.14

unt

-0.14

unt

-0.14

ICODE

-0.14

asan

-0.14

achten

-0.13

 à¤¤à¤¹

-0.13

POSITIVE LOGITS

Wiki

0.17

wiki

0.16

£½

0.14

 Wiki

0.14

rollers

0.14

ira

0.14

 Schneider

0.14

rove

0.13

Vy

0.13

Activations Density 0.228%

elements related to specific institutions and their functions

No Comments

No Known Activations