INDEX

Explanations

expressions of uncertainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

alink

-0.14

imals

-0.14

erox

-0.14

ÐµÐ½ÑĮÑİ

-0.14

egment

-0.14

Ð½Ð³

-0.13

.dds

-0.13

ams

-0.13

ÐµÑĢÐ¸Ð½

-0.13

atern

-0.13

POSITIVE LOGITS

 exact

0.15

now

0.14

exact

0.14

alla

0.14

 sire

0.14

 gourmet

0.14

UA

0.14

LTR

0.14

 necessarily

0.13

è¦º

0.13

Activations Density 0.064%

expressions of uncertainty or doubt

No Comments

No Known Activations