INDEX

Explanations

references to cars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

elyn

-0.18

tems

-0.18

esc

-0.17

kl

-0.17

enburg

-0.16

gil

-0.15

estone

-0.15

enz

-0.15

rana

-0.14

ka

-0.14

POSITIVE LOGITS

abin

0.25

ibbean

0.24

avan

0.22

riages

0.22

cter

0.21

acter

0.20

bohydr

0.20

acters

0.19

riage

0.18

afe

0.18

Activations Density 0.021%

references to cars

No Comments

No Known Activations