INDEX

Explanations

phrases related to instructions or guidance on handling situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

èŃľ

-0.17

 alike

-0.15

egers

-0.15

 crest

-0.15

isay

-0.15

 unloaded

-0.15

reh

-0.14

.rl

-0.14

Ã©rc

-0.14

Ã«n

-0.14

POSITIVE LOGITS

0.18

imei

0.15

tone

0.15

gL

0.14

 Ling

0.14

 Dual

0.14

ÑģÐµ

0.14

fish

0.14

iques

0.14

Activations Density 0.011%

phrases related to instructions or guidance on handling situations

No Comments

No Known Activations