INDEX

Explanations

references to obedience and compliance to authority

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

ÑģÑĤÑĭ

-0.16

à¹Īà¸²à¸¢

-0.16

 Lomb

-0.16

sth

-0.15

 Engel

-0.14

enburg

-0.14

olio

-0.14

Ø¹

-0.14

ãĥ§

-0.14

irler

-0.14

POSITIVE LOGITS

urate

0.16

ÃŃch

0.16

eel

0.16

currentColor

0.15

 sexist

0.15

longleftrightarrow

0.14

FUL

0.14

Batch

0.14

.opendaylight

0.14

cott

0.13

Activations Density 0.006%

references to obedience and compliance to authority

No Comments

No Known Activations