INDEX

Explanations

specific terms related to medical conditions and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

itel

-0.18

ulan

-0.17

ighton

-0.15

gram

-0.14

åĽ³

-0.14

 onCreateView

-0.14

-fw

-0.14

 Truy

-0.14

\Collections

-0.14

omial

-0.14

POSITIVE LOGITS

rico

0.17

Abs

0.15

 polar

0.15

abs

0.15

lops

0.14

 absolute

0.14

ÏĢÏĮ

0.14

ì§Ģê³ł

0.14

 Burns

0.14

osi

0.14

Activations Density 0.001%

specific terms related to medical conditions and their attributes

No Comments

No Known Activations