INDEX

Explanations

references to pie, particularly in various contexts and formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ship

-0.20

meer

-0.16

.GetResponse

-0.16

sing

-0.15

ised

-0.15

ëį°

-0.15

udd

-0.14

ned

-0.14

ioned

-0.14

Maz

-0.14

POSITIVE LOGITS

pie

0.18

urette

0.17

ÑĤÐ¾ÑĢ

0.15

 Slice

0.15

antic

0.15

ALCHEMY

0.15

onder

0.15

blr

0.15

etter

0.15

alnÄ±z

0.14

Activations Density 0.015%

references to pie, particularly in various contexts and formats

No Comments

No Known Activations