INDEX

Explanations

references to government officials, particularly commissioners

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

yy

-0.18

INGER

-0.17

ansen

-0.16

che

-0.15

Che

-0.15

Pep

-0.15

inger

-0.15

fc

-0.15

ampler

-0.14

com

-0.14

POSITIVE LOGITS

illos

0.15

xford

0.15

unch

0.15

hoff

0.14

umbo

0.14

 ÑĨÐµÐ»

0.14

/lic

0.14

ess

0.14

ÅĻi

0.13

 ÑģÐµÐ±

0.13

Activations Density 0.005%

references to government officials, particularly commissioners

No Comments

No Known Activations