INDEX

Explanations

repetitive or comparative phrases indicating similarity and difference

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

seau

-0.15

anford

-0.15

tet

-0.15

yro

-0.14

pong

-0.14

dependencies

-0.14

Ð¡Ð¡Ðł

-0.14

Ð°Ð½Ð³

-0.14

Verifier

-0.14

doing

-0.14

POSITIVE LOGITS

 justice

0.35

 Justice

0.25

job

0.25

justice

0.24

 things

0.24

 thing

0.23

 damage

0.23

 wrong

0.23

 jobs

0.22

cket

0.21

Activations Density 0.174%

repetitive or comparative phrases indicating similarity and difference

No Comments

No Known Activations