INDEX

Explanations

proper nouns, particularly names of individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

arms

-0.16

ettel

-0.15

'gc

-0.14

)init

-0.14

dum

-0.14

olume

-0.13

low

-0.13

ichtig

-0.13

å¼ĺ

-0.13

 Arms

-0.13

POSITIVE LOGITS

.getSeconds

0.13

 Imperial

0.13

 Jerome

0.13

bv

0.13

 Rooney

0.13

 tÆ°

0.13

éĩĩ

0.13

ÃľR

0.13

ocale

0.13

stein

0.13

Activations Density 0.512%

proper nouns, particularly names of individuals and entities

No Comments

No Known Activations