INDEX

Explanations

dialogue and conversational phrases in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Alias

-0.15

 ãĥĶ

-0.15

Ã¡b

-0.15

lÃ½

-0.15

oeff

-0.14

ephir

-0.14

legg

-0.14

PIO

-0.14

kb

-0.14

POSITIVE LOGITS

 Gems

0.13

Ø§Ø¹Ø¯

0.13

.spin

0.13

Ð»Ð¸ÑĤ

0.12

Ã³m

0.12

 quit

0.12

mau

0.12

neb

0.12

 ÙĪÙĦØ¯

0.12

Activations Density 0.113%

dialogue and conversational phrases in the text

No Comments

No Known Activations