INDEX

Explanations

terms related to operational modes and performance states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

/script

-0.15

 ÙĪØ¬Ùĩ

-0.14

umo

-0.14

 fren

-0.13

ØªØ²

-0.13

.objects

-0.13

 Äĳá»©ng

-0.13

 pornos

-0.13

 fortune

-0.13

Live

-0.12

POSITIVE LOGITS

 mode

0.21

 status

0.21

 state

0.20

çĬ¶æĢģ

0.18

 stage

0.17

kovi

0.17

æľŁ

0.16

 period

0.16

-mode

0.16

 lasting

0.16

Activations Density 0.216%

terms related to operational modes and performance states

No Comments

No Known Activations