INDEX

Explanations

terms and phrases related to forecasting or making predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ushed

-0.17

rema

-0.15

ermann

-0.14

unte

-0.14

aign

-0.14

USH

-0.14

-0.13

ported

-0.13

POSITIVE LOGITS

 loose

0.17

nis

0.17

ito

0.16

ãĥ³ãĥĦ

0.16

 forecast

0.15

 loos

0.15

 Engel

0.14

avers

0.14

.ident

0.14

cl

0.14

Activations Density 0.042%

terms and phrases related to forecasting or making predictions

No Comments

No Known Activations