INDEX

Explanations

references to various types of warriors and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

olas

-0.16

AGMA

-0.15

gart

-0.15

iday

-0.15

HEL

-0.14

ogg

-0.14

side

-0.14

Ð²Ð¾ÑĢ

-0.14

nbsp

-0.14

deki

-0.14

POSITIVE LOGITS

ess

0.22

esses

0.20

ry

0.19

bane

0.19

ovnÄĽ

0.17

like

0.15

gram

0.15

rello

0.14

cry

0.14

ically

0.14

Activations Density 0.075%

references to various types of warriors and their characteristics

No Comments

No Known Activations