INDEX

Explanations

occurrences of the name "Philip" or related variations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ertura

-0.16

"":

-0.15

vette

-0.14

daq

-0.14

ional

-0.14

imals

-0.14

ãĤīãģı

-0.14

charg

-0.14

uteur

-0.14

mittel

-0.14

POSITIVE LOGITS

pe

0.28

ppe

0.22

ps

0.20

ipp

0.18

pos

0.18

ipe

0.18

ippi

0.17

pon

0.17

pen

0.17

pron

0.16

Activations Density 0.007%

occurrences of the name "Philip" or related variations in the text

No Comments

No Known Activations