INDEX

Explanations

instances of the apostrophe character used in contractions or possessives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.22

&nbsp

-0.17

%s

-0.15

holm

-0.15

'E

-0.14

'in

-0.14

'Â´

-0.14

’n

-0.14

'n

-0.14

ierz

-0.14

POSITIVE LOGITS

til

0.29

neath

0.28

bout

0.26

0.25

cause

0.25

cept

0.24

round

0.23

Activations Density 0.032%

instances of the apostrophe character used in contractions or possessives

No Comments

No Known Activations