INDEX

Explanations

expressions of unexpected situations and community responses to challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

reesome

-0.15

'RE

-0.14

 voks

-0.13

ãģıãĤĭ

-0.13

olic

-0.13

ãģķãĤĮãĤĭ

-0.13

ãĤīãĤĮãĤĭ

-0.12

ãģ«ãģªãĤĭ

-0.12

ãĤıãĤĮãĤĭ

-0.12

.Guna

-0.12

POSITIVE LOGITS

has

0.72

 have

0.62

 telah

0.59

has

0.58

've

0.57

’ve

0.57

 ÄĳÃ£

0.57

 hasn

0.53

have

0.51

has

0.51

Activations Density 1.329%

expressions of unexpected situations and community responses to challenges

No Comments

No Known Activations