INDEX

Explanations

specific dates and numerical references

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

alet

-0.16

elmet

-0.15

olv

-0.15

gcd

-0.15

eness

-0.14

ohl

-0.14

resh

-0.14

-0.13

urdu

-0.13

eson

-0.13

POSITIVE LOGITS

colo

0.15

odos

0.14

 Mobil

0.14

¬Ĥ

0.14

 Ð¿Ð¾Ð´Ð²

0.13

groundColor

0.13

ierge

0.13

quot

0.13

ahren

0.13

cki

0.13

Activations Density 0.007%

specific dates and numerical references

No Comments

No Known Activations