INDEX

Explanations

terms related to watch features and measurements

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

ronym

-0.17

inery

-0.16

ajs

-0.14

Ĥæķ°

-0.14

olas

-0.14

ajas

-0.14

rias

-0.14

.hom

-0.13

emann

-0.13

hem

-0.13

POSITIVE LOGITS

inth

0.15

osate

0.15

geh

0.15

ãĤ®

0.14

ãĥ¼ãĥģ

0.14

åŁŁ

0.14

æ®µ

0.14

 Clyde

0.14

IRC

0.13

esy

0.13

Activations Density 0.008%

terms related to watch features and measurements

No Comments

No Known Activations