INDEX

Explanations

actions related to providing services and creating positive outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

uez

-0.15

egasus

-0.14

educt

-0.14

kla

-0.14

ä»ĭ

-0.13

aea

-0.13

omo

-0.13

 meaning

-0.13

POSITIVE LOGITS

 simultaneously

0.18

ctal

0.17

 ALSO

0.16

erman

0.15

Īëĭ¤

0.15

 simult

0.14

ãĥ³ãĤº

0.14

ceb

0.14

stdin

0.14

 addCriterion

0.14

Activations Density 0.060%

actions related to providing services and creating positive outcomes

No Comments

No Known Activations