INDEX

Explanations

references to dates or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

chied

-0.16

etti

-0.14

seg

-0.14

alsa

-0.14

ģm

-0.13

 tether

-0.13

iniz

-0.13

mile

-0.13

Seg

-0.13

\Eloquent

-0.13

POSITIVE LOGITS

aille

0.16

æģ

0.14

 ÐĿÑĥ

0.14

"math

0.14

DISABLE

0.13

ITTE

0.13

iad

0.13

Ø§Ø³Ùĩ

0.13

reme

0.13

ãģ³

0.13

Activations Density 0.038%

references to dates or time periods

No Comments

No Known Activations