INDEX

Explanations

references to violence or bloodshed

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.15

 hind

-0.15

vic

-0.15

/post

-0.14

hed

-0.14

à¥Ģà¤Łà¤°

-0.14

 closing

-0.14

nal

-0.14

LANG

-0.14

 bells

-0.14

POSITIVE LOGITS

rios

0.18

combe

0.17

tember

0.15

 Tradition

0.15

 predecess

0.15

iaux

0.15

enschaft

0.15

letcher

0.14

arters

0.14

aday

0.13

Activations Density 0.013%

references to violence or bloodshed

No Comments

No Known Activations