INDEX

Explanations

topics related to health and digital wellness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ago

-0.16

èĦ±

-0.15

-0.14

éģ

-0.14

SupportedContent

-0.14

.manual

-0.14

Ø²ÙĨ

-0.14

anch

-0.13

MOOTH

-0.13

alli

-0.13

POSITIVE LOGITS

 itself

0.21

erosis

0.16

-specific

0.16

vana

0.16

 proper

0.15

vs

0.15

 Bris

0.15

 samot

0.15

VS

0.14

 specific

0.14

Activations Density 0.341%

topics related to health and digital wellness

No Comments

No Known Activations