INDEX

Explanations

health-related terminology, especially in the context of diseases and infections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ETCH

-0.16

apat

-0.16

à¥ĩà¤¯

-0.15

genesis

-0.15

 bore

-0.14

ilater

-0.14

aska

-0.14

Flip

-0.14

 Chun

-0.14

POSITIVE LOGITS

(___

0.15

_phys

0.15

 Reform

0.15

spi

0.15

<TResult

0.14

ensburg

0.14

hay

0.13

ÎµÏĢ

0.13

 Nicol

0.13

 outer

0.13

Activations Density 0.155%

health-related terminology, especially in the context of diseases and infections

No Comments

No Known Activations