INDEX

Explanations

phrases indicating personal experiences and identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

kontakte

-0.16

loha

-0.14

redient

-0.14

.shell

-0.14

essaging

-0.14

illian

-0.14

yaw

-0.14

aeper

-0.13

FP

-0.13

iene

-0.13

POSITIVE LOGITS

 himself

0.55

 themselves

0.55

 herself

0.52

 ourselves

0.50

 itself

0.48

èĩªå·±

0.47

 Himself

0.47

èĩªèº«

0.47

 myself

0.47

own

0.45

Activations Density 0.308%

phrases indicating personal experiences and identities

No Comments

No Known Activations