INDEX

Explanations

references to military or government departments and their related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

?,?,?,?,

-0.18

 Various

-0.17

 various

-0.16

roma

-0.15

Various

-0.15

XC

-0.14

ģ

-0.14

rompt

-0.14

 Exclusive

-0.13

iesta

-0.13

POSITIVE LOGITS

two

0.19

two

0.18

ëĳĺ

0.17

ä¸¤äºº

0.17

ä¸¤

0.17

 Ð´Ð²Ðµ

0.16

ONS

0.16

 ëĳĺ

0.16

Two

0.16

ä¸¤ä¸ª

0.16

Activations Density 0.150%

references to military or government departments and their related activities

No Comments

No Known Activations