INDEX

Explanations

statements about problems or complexities faced in various situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÏĥÏĦÎ±

-0.15

lek

-0.15

-0.14

uture

-0.14

 hallmark

-0.14

 synonym

-0.13

.answers

-0.13

UTURE

-0.13

hani

-0.13

 foregoing

-0.13

POSITIVE LOGITS

 catch

0.63

 catches

0.52

 Catch

0.50

catch

0.49

Catch

0.48

 twist

0.43

 catching

0.39

 caught

0.36

	catch

0.36

.catch

0.35

Activations Density 0.106%

statements about problems or complexities faced in various situations

No Comments

No Known Activations