INDEX

Explanations

locations and their relationships, particularly in a medical and travel context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

COPE

-0.17

leton

-0.16

chte

-0.14

Kit

-0.14

 Provincial

-0.14

ohon

-0.14

ibel

-0.14

PLE

-0.14

acho

-0.14

gable

-0.14

POSITIVE LOGITS

Rew

0.19

 Ranch

0.19

Rew

0.19

ruk

0.18

Luck

0.18

Kup

0.18

gren

0.17

 Luck

0.17

 Salem

0.17

Dum

0.17

Activations Density 0.190%

locations and their relationships, particularly in a medical and travel context

No Comments

No Known Activations