INDEX

Explanations

terms related to medical procedures and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

|string

-0.15

Ãªnh

-0.15

ÙĦÙĪ

-0.14

ÐµÑĢÐ¿

-0.14

ÐµÐ»Ð°

-0.14

Ã¤Ã¤

-0.14

cratch

-0.14

lu

-0.14

xCA

-0.13

 Ð³Ð°Ð»

-0.13

POSITIVE LOGITS

phia

0.17

 tavs

0.14

 Brill

0.13

Î¯Î¶

0.13

 USHORT

0.13

tae

0.13

 Ð²ÑĢÐµÐ¼ÐµÐ½Ð¸

0.13

 Winn

0.13

 erotik

0.12

 çŁ

0.12

Activations Density 0.004%

terms related to medical procedures and organizational structures

No Comments

No Known Activations