INDEX

Explanations

words related to vehicles or driving

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

kl

-0.17

ym

-0.16

elyn

-0.16

tems

-0.15

rand

-0.15

etu

-0.15

imet

-0.15

HEME

-0.15

aina

-0.15

ihn

-0.14

POSITIVE LOGITS

cter

0.25

acter

0.22

abin

0.20

isma

0.19

acters

0.17

itative

0.17

DS

0.16

erer

0.16

antan

0.16

ossier

0.16

Activations Density 0.014%

words related to vehicles or driving

No Comments

No Known Activations