INDEX

Explanations

phrases that indicate a time period, particularly the word "During."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/by

-0.19

clud

-0.16

aways

-0.15

sha

-0.14

olas

-0.13

verter

-0.13

ns

-0.13

ÃŃt

-0.13

++.

-0.13

anut

-0.13

POSITIVE LOGITS

 Ð¶Ðµ

0.16

dale

0.15

ipa

0.15

.TryParse

0.14

RIX

0.14

æµ¦

0.14

duk

0.13

istrovstvÃŃ

0.13

IMAL

0.13

 decades

0.13

Activations Density 0.084%

phrases that indicate a time period, particularly the word "During."

No Comments

No Known Activations