INDEX

Explanations

expressions of hope and uncertainty

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

hari

-0.15

robat

-0.15

Å¾ÃŃ

-0.14

_snapshot

-0.14

.rpm

-0.13

UNUSED

-0.13

eniz

-0.13

 Replies

-0.13

indsight

-0.13

buat

-0.13

POSITIVE LOGITS

 hope

1.09

 hopes

0.96

 Hope

0.93

hope

0.91

Hope

0.88

 hoping

0.81

 hoped

0.79

å¸ĮæľĽ

0.73

 hopeful

0.65

HO

0.61

Activations Density 0.322%

expressions of hope and uncertainty

No Comments

No Known Activations