INDEX

Explanations

references to visual media and images in various contexts

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

soever

-0.18

ennie

-0.16

eping

-0.15

ë°©

-0.15

 punct

-0.14

eer

-0.14

ia

-0.14

bc

-0.14

zek

-0.14

rina

-0.13

POSITIVE LOGITS

ewe

0.16

ãĥ¼ãĥĭ

0.15

_ANDROID

0.15

allen

0.15

è´¨

0.14

ToLeft

0.14

kili

0.14

.InnerException

0.14

jez

0.14

ason

0.14

Activations Density 0.056%

references to visual media and images in various contexts

No Comments

No Known Activations