INDEX

Explanations

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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÙıÙĪ

-0.15

uten

-0.15

ille

-0.15

eneg

-0.15

-0.14

<data

-0.14

ãĥģãĥ¥

-0.14

 ÑģÐ¾Ð±Ð¾Ñİ

-0.14

.sponge

-0.14

POSITIVE LOGITS

apr

0.17

quo

0.14

til

0.14

 Band

0.14

isti

0.14

inea

0.14

abo

0.13

Clr

0.13

Fetching

0.13

å·¥

0.13

Activations Density 0.051%

dates and numerical references

No Comments

No Known Activations