INDEX

Explanations

reference to data and its dissemination or usage in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÙĪÙĨÙĩ

-0.19

azen

-0.17

olla

-0.17

à¥Ŀ

-0.16

ample

-0.16

astics

-0.15

.jquery

-0.15

ipel

-0.15

 ÑĢÐ°Ð²Ð½Ð¾

-0.15

ãĥ¼ãĤº

-0.15

POSITIVE LOGITS

span

0.18

viz

0.17

 span

0.16

 across

0.16

aman

0.15

(.)

0.15

 spans

0.15

 ç©

0.14

nos

0.14

IDO

0.14

Activations Density 0.004%

reference to data and its dissemination or usage in various contexts

No Comments

No Known Activations