INDEX

Explanations

occurrences of the word "Journal" and related terms indicating academic or professional publications

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

ewn

-0.17

asser

-0.17

zk

-0.16

ext

-0.15

coe

-0.15

ertools

-0.15

ulos

-0.15

ater

-0.15

ets

-0.15

POSITIVE LOGITS

istic

0.31

ists

0.28

ism

0.24

isms

0.23

istics

0.23

ize

0.23

istically

0.23

isted

0.22

ISM

0.21

izing

0.21

Activations Density 0.020%

occurrences of the word "Journal" and related terms indicating academic or professional publications

No Comments

No Known Activations