INDEX

Explanations

terms related to numerical values and calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ø§Ø©

-0.14

erator

-0.14

ynos

-0.14

.createFrom

-0.14

 Salisbury

-0.14

IRS

-0.14

ItemAt

-0.13

mentation

-0.13

 Tanner

-0.13

bai

-0.13

POSITIVE LOGITS

feld

0.17

ith

0.16

rove

0.15

inue

0.15

eryl

0.15

çĩŁ

0.15

anya

0.15

 Tato

0.14

ëıĮ

0.14

ĭ

0.14

Activations Density 0.094%

terms related to numerical values and calculations

No Comments

No Known Activations

terms related to numerical values and calculations

No Comments

No Known Activations