INDEX

Explanations

negations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

raj

-0.16

-0.14

acle

-0.14

 Narrow

-0.13

anner

-0.13

è£ľ

-0.13

æĪ

-0.13

ague

-0.13

onia

-0.13

 Pending

-0.13

POSITIVE LOGITS

mie

0.16

åħ¸

0.15

to

0.14

æ

0.14

pheres

0.14

etim

0.14

abar

0.14

åĪ°çļĦ

0.13

 Ø¹ÙĤ

0.13

YPRE

0.13

Activations Density 0.009%

negations in the text

No Comments

No Known Activations