INDEX

Explanations

phrases indicating surpassing limits or expectations

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

IRO

-0.17

rack

-0.17

iros

-0.15

isch

-0.15

 Aeros

-0.14

drop

-0.14

cone

-0.14

à¤Ĺà¤²

-0.14

Nut

-0.14

ÏĢÎ¿

-0.14

POSITIVE LOGITS

ambre

0.14

ioni

0.14

ap

0.14

Ð¸ÑģÑĤÑĢÐ°

0.14

 Guth

0.14

-ln

0.14

0.13

ettle

0.13

Activations Density 0.032%

phrases indicating surpassing limits or expectations

No Comments

No Known Activations