INDEX

Explanations

words related to the actions and impacts of processes or events

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Rough

-0.15

-0.14

Äį

-0.14

 rough

-0.14

jong

-0.14

ott

-0.13

 Platt

-0.13

 inorder

-0.13

xies

-0.13

ff

-0.13

POSITIVE LOGITS

vais

0.20

RefPtr

0.14

ëł¥ìĿĦ

0.14

à¸¹à¸ĩ

0.14

ritz

0.14

iband

0.13

 ApplicationException

0.13

 ActiveForm

0.13

eron

0.13

riet

0.13

Activations Density 0.525%

words related to the actions and impacts of processes or events

No Comments

No Known Activations