INDEX

Explanations

names of political figures and government officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ã¶g

-0.16

\Bundle

-0.15

olini

-0.14

weit

-0.14

.hr

-0.14

Ã±a

-0.14

ieux

-0.14

 bevor

-0.13

 Bucc

-0.13

yne

-0.13

POSITIVE LOGITS

urret

0.15

ãĤ©

0.14

 hurt

0.14

issor

0.14

solete

0.13

_Impl

0.13

Ð²ÐµÑī

0.13

ende

0.13

Activations Density 0.059%

names of political figures and government officials

No Comments

No Known Activations