INDEX

Explanations

phrases indicating uncertainty or conditionality

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

dur

-0.14

 defaultProps

-0.14

eller

-0.14

 themselves

-0.14

 Jord

-0.14

utors

-0.14

itta

-0.14

nev

-0.13

ERA

-0.13

ollo

-0.13

POSITIVE LOGITS

ä¹Łæĺ¯

0.21

 ones

0.16

tant

0.16

nite

0.15

 something

0.15

worthy

0.15

HDR

0.15

something

0.14

 worth

0.14

 occurred

0.14

Activations Density 0.245%

phrases indicating uncertainty or conditionality

No Comments

No Known Activations