INDEX

Explanations

metrics related to educational rankings and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

æĸ

-0.15

igos

-0.15

emax

-0.15

ABCDEFG

-0.15

 Phon

-0.15

Mod

-0.14

hle

-0.14

shade

-0.14

zell

-0.14

å¼ı

-0.14

POSITIVE LOGITS

 worldwide

0.18

 nationwide

0.18

erece

0.15

 overall

0.15

 Nationwide

0.14

iten

0.14

overall

0.14

Ã±o

0.14

DidChange

0.14

Activations Density 0.052%

metrics related to educational rankings and recognition

No Comments

No Known Activations