INDEX

Explanations

phrases related to forward-looking statements or predictions about future events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

APO

-0.15

ignum

-0.15

 Exist

-0.14

 Wars

-0.14

antic

-0.14

ibo

-0.14

gim

-0.13

ORIZATION

-0.13

hold

-0.13

 wait

-0.13

POSITIVE LOGITS

quir

0.17

otime

0.17

å¼

0.15

ä¼į

0.15

pta

0.15

olis

0.15

å²³

0.14

 lá»ĩ

0.14

ä¼

0.14

hra

0.14

Activations Density 0.005%

phrases related to forward-looking statements or predictions about future events

No Comments

No Known Activations