INDEX

Explanations

references to significant or large-scale events or objects

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

othermal

-0.17

Ð¾Ð¿Ð¸Ñģ

-0.17

ocking

-0.15

erman

-0.15

andering

-0.15

deki

-0.14

untime

-0.14

InstanceState

-0.14

otope

-0.14

prus

-0.14

POSITIVE LOGITS

avit

0.18

eur

0.17

erie

0.16

0.15

lake

0.15

ests

0.14

Ä±s

0.14

Ced

0.14

essa

0.13

ÑĩÐ°Ð¹

0.13

Activations Density 0.020%

references to significant or large-scale events or objects

No Comments

No Known Activations