INDEX

Explanations

structured format indicators and references typically seen in academic articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ë§ī

-0.15

airo

-0.15

ially

-0.15

aly

-0.14

eniz

-0.14

si

-0.14

_SERIAL

-0.14

isay

-0.14

ly

-0.14

ally

-0.14

POSITIVE LOGITS

oyer

0.16

Ø±Ø²

0.15

bis

0.15

 flip

0.15

apk

0.15

 Flip

0.15

Mos

0.15

antz

0.14

ande

0.14

Activations Density 0.007%

structured format indicators and references typically seen in academic articles

No Comments

No Known Activations