INDEX

Explanations

terms related to neurology and neurological fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

CTIONS

-0.17

anter

-0.16

anity

-0.16

-0.15

udeau

-0.15

rogram

-0.15

oyer

-0.15

 ä»¶

-0.14

zew

-0.14

revision

-0.14

POSITIVE LOGITS

enstein

0.15

 Grave

0.15

áº§m

0.15

 pena

0.14

 Schwarz

0.14

mscorlib

0.14

 DbSet

0.13

ÏĮÎ³

0.13

enga

0.13

OrCreate

0.13

Activations Density 0.002%

terms related to neurology and neurological fields

No Comments

No Known Activations