INDEX

Explanations

percentages related to statistical data or performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

atch

-0.16

ften

-0.16

ĤŃ

-0.14

iferay

-0.14

ovice

-0.14

icare

-0.14

uns

-0.14

hoo

-0.14

ILLE

-0.14

Ced

-0.13

POSITIVE LOGITS

oriously

0.20

rale

0.18

éĲĺ

0.17

-plus

0.16

lobal

0.16

0.15

iles

0.14

----------------------------------------------------------------------------

0.14

ãĥªãĥ³ãĤ°

0.14

aversable

0.14

Activations Density 0.016%

percentages related to statistical data or performance metrics

No Comments

No Known Activations