INDEX

Explanations

highly contextual and relational keywords indicating actions, intentions, or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Buck

-0.17

 å®®

-0.16

IRR

-0.16

iston

-0.15

bucks

-0.15

 bucks

-0.15

ipel

-0.15

oston

-0.14

åŃ

-0.14

itti

-0.14

POSITIVE LOGITS

unya

0.16

dil

0.15

 lever

0.14

åĭĴ

0.14

áº¡t

0.14

ÑİÐ½

0.14

vester

0.14

 soci

0.13

inton

0.13

 Soci

0.13

Activations Density 0.001%

highly contextual and relational keywords indicating actions, intentions, or conditions

No Comments

No Known Activations