INDEX

Explanations

references to individuals in authoritative or leadership roles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ambi

-0.18

.ua

-0.17

Ķ

-0.16

fl

-0.16

ilage

-0.15

ãĥ¼ãĥ©

-0.15

rating

-0.14

ãģªãĤĭ

-0.14

rug

-0.14

antage

-0.14

POSITIVE LOGITS

 Linden

0.15

Ø³Ùĥ

0.15

opis

0.15

/generated

0.14

tember

0.14

berman

0.14

.decorate

0.14

Ð»Ð¸Ñı

0.13

 backed

0.13

spoken

0.13

Activations Density 0.108%

references to individuals in authoritative or leadership roles

No Comments

No Known Activations