INDEX

Explanations

punctuation marks, particularly periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

å¹¹

-0.16

ixo

-0.15

 Sher

-0.15

itung

-0.14

orro

-0.14

ãĤĦãģĻ

-0.14

ost

-0.14

stry

-0.14

istra

-0.14

POSITIVE LOGITS

Î¯ÏīÎ½

0.15

phis

0.15

errat

0.15

Ø±ÙĪØ²

0.15

osci

0.15

Ã¡lo

0.15

 biÃªn

0.14

æ£®

0.14

woff

0.14

nton

0.14

Activations Density 0.004%

punctuation marks, particularly periods

No Comments

No Known Activations