INDEX

Explanations

mentions of specific names or proper nouns related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

er

-0.27

-0.26

-0.20

een

-0.19

ing

-0.19

oxy

-0.18

otic

-0.17

oq

-0.16

eria

-0.16

echn

-0.16

POSITIVE LOGITS

ipeg

0.26

ings

0.25

sylvania

0.23

nn

0.23

ovation

0.22

ibal

0.22

ery

0.22

ounced

0.21

iversary

0.21

egan

0.20

Activations Density 0.030%

mentions of specific names or proper nouns related to individuals

No Comments

No Known Activations