INDEX

Explanations

phrases related to safe practices and reliable methods

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

-piece

-0.17

aleigh

-0.16

tif

-0.15

å®¾

-0.15

Ð¶Ñĥ

-0.15

ÐµÐ»ÐµÑĦ

-0.14

 Aires

-0.14

VOKE

-0.14

resa

-0.14

 ontvangst

-0.14

POSITIVE LOGITS

ernes

0.15

afen

0.15

DR

0.15

çī

0.15

 safely

0.14

ably

0.14

 coloring

0.14

 Koch

0.13

 Levy

0.13

Activations Density 0.004%

phrases related to safe practices and reliable methods

No Comments

No Known Activations