INDEX

Explanations

references to specific dates, times, and locations for events

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

anders

-0.16

orough

-0.16

udd

-0.16

 Lawson

-0.15

readcr

-0.15

 Freund

-0.15

mpr

-0.14

auc

-0.14

OMB

-0.14

zos

-0.14

POSITIVE LOGITS

ula

0.15

ÑħÐ¸

0.15

izia

0.14

Î¹Î¿

0.14

 povol

0.14

ende

0.14

0.13

ÙĦÛĮ

0.13

ilen

0.13

Activations Density 0.006%

references to specific dates, times, and locations for events

No Comments

No Known Activations