INDEX

Explanations

mentions of awards, honors, and notable achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

inci

-0.14

uyla

-0.14

untu

-0.14

-0.13

alu

-0.13

à¸§à¸Ķ

-0.13

Äı

-0.13

byt

-0.13

indr

-0.13

olla

-0.13

POSITIVE LOGITS

êµ

0.15

oplayer

0.14

caps

0.14

 HÃ¼s

0.14

 Caps

0.14

ROWSER

0.13

_configs

0.13

ãĥ¼ãĥĨãĤ£

0.13

à¸²à¸ĩ

0.12

argin

0.12

Activations Density 0.051%

mentions of awards, honors, and notable achievements

No Comments

No Known Activations