INDEX

Explanations

terms related to medical conditions and their complexities

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

iano

-0.16

iek

-0.14

mom

-0.14

 Brom

-0.13

declspec

-0.13

irable

-0.13

OMX

-0.13

Ð½Ñĥ

-0.12

 ä»Ĭ

-0.12

 Pent

-0.12

POSITIVE LOGITS

eti

0.17

nos

0.15

ients

0.14

Ã¤hlt

0.14

Ã¶y

0.14

 cases

0.14

ched

0.14

aptop

0.14

orrar

0.14

seen

0.14

Activations Density 0.035%

terms related to medical conditions and their complexities

No Comments

No Known Activations