INDEX

Explanations

references to a fast-paced environment or narrative style

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

rosse

-0.17

éļ

-0.16

olie

-0.15

auga

-0.15

Ã¼z

-0.15

tring

-0.15

.GetString

-0.14

udic

-0.14

threads

-0.14

kara

-0.14

POSITIVE LOGITS

ey

0.16

 Kumar

0.16

oint

0.15

 Salmon

0.14

ÐµÑİ

0.14

interop

0.14

otti

0.14

nik

0.13

kte

0.13

Activations Density 0.002%

references to a fast-paced environment or narrative style

No Comments

No Known Activations