INDEX

Explanations

references to the term "Black" in various contexts, possibly related to culture, identity, or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ico

-0.18

ito

-0.17

ianne

-0.16

uv

-0.15

illery

-0.15

getti

-0.15

 Outer

-0.14

Ã¹ng

-0.14

Ã³nica

-0.14

bserv

-0.14

POSITIVE LOGITS

 Panther

0.21

adder

0.21

pink

0.20

 Sabbath

0.20

adders

0.20

 Lives

0.19

board

0.18

alic

0.18

_mirror

0.18

-Owned

0.17

Activations Density 0.017%

references to the term "Black" in various contexts, possibly related to culture, identity, or events

No Comments

No Known Activations