INDEX

Explanations

terms associated with illness and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

uÄį

-0.16

_callable

-0.16

ãĤ¥

-0.16

kv

-0.15

å¼ĺ

-0.14

ptal

-0.14

åºŃ

-0.14

.FONT

-0.13

AMP

-0.13

doch

-0.13

POSITIVE LOGITS

 meaning

0.16

 fancy

0.16

ì¦

0.15

 ones

0.15

0.14

asis

0.14

neb

0.14

igen

0.14

aler

0.14

-go

0.14

Activations Density 0.137%

terms associated with illness and their implications

No Comments

No Known Activations