INDEX

Explanations

phrases indicating sources or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

quete

-0.15

illo

-0.14

igated

-0.14

ilia

-0.14

obia

-0.14

è·Ŀ

-0.14

nap

-0.14

iversal

-0.13

ngine

-0.13

upert

-0.13

POSITIVE LOGITS

ovice

0.17

èĢĮ

0.16

/Form

0.15

ktop

0.14

etest

0.14

emade

0.14

iage

0.14

eteor

0.14

ispens

0.14

 èĢĮ

0.14

Activations Density 0.034%

phrases indicating sources or references

No Comments

No Known Activations