INDEX

Explanations

repeated characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Indigenous

-0.15

pos

-0.14

.updateDynamic

-0.14

jah

-0.13

 Aside

-0.13

.compat

-0.13

 Helpful

-0.13

eki

-0.13

 snag

-0.13

sug

-0.13

POSITIVE LOGITS

Se

0.27

 atleast

0.21

Se

0.18

 equipments

0.18

 Jerry

0.17

-Se

0.17

 FUCK

0.16

infeld

0.16

 fucking

0.16

 upto

0.15

Activations Density 0.003%

repeated characters or symbols

No Comments

No Known Activations