INDEX

Explanations

instances of personal pronouns and expressions of uncertainty or lack of knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

utdown

-0.15

_almost

-0.15

ura

-0.14

åŀ

-0.14

ugins

-0.14

ymm

-0.14

oubles

-0.14

resi

-0.13

=title

-0.13

Jag

-0.13

POSITIVE LOGITS

ä¸įçŁ¥éģĵ

0.36

 unknown

0.35

 descon

0.34

unknown

0.33

don

0.31

Unknown

0.31

 Unknown

0.30

 UNKNOWN

0.30

 unsure

0.29

_unknown

0.28

Activations Density 0.231%

instances of personal pronouns and expressions of uncertainty or lack of knowledge

No Comments

No Known Activations