INDEX

Explanations

references to categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

iola

-0.15

ħ§

-0.14

ildo

-0.14

adio

-0.13

Î³Î±

-0.13

erton

-0.13

ago

-0.13

.sa

-0.13

oc

-0.13

PPER

-0.13

POSITIVE LOGITS

inar

0.20

bau

0.17

arrera

0.15

ethe

0.14

 sá»±

0.14

arrant

0.14

 aktual

0.14

 Buccane

0.14

ÐºÑĥÐ²Ð°Ð½Ð½Ñı

0.14

fonts

0.14

Activations Density 0.000%

references to categories or classifications

No Comments

No Known Activations