INDEX

Explanations

descriptions of contrasts or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

emer

-0.16

Ã¤t

-0.15

ientes

-0.15

 Lace

-0.14

oling

-0.14

Ã¡tico

-0.14

atron

-0.14

.plus

-0.14

orno

-0.14

roller

-0.14

POSITIVE LOGITS

 similarly

0.28

Similarly

0.26

 Similarly

0.25

 Likewise

0.21

Lik

0.20

 analog

0.18

 similar

0.18

 likewise

0.18

 same

0.18

 Analog

0.17

Activations Density 0.175%

descriptions of contrasts or comparisons

No Comments

No Known Activations