INDEX

Explanations

quotation marks and symbols related to dialogue or speech

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

hek

-0.17

akov

-0.16

lum

-0.16

heimer

-0.16

ourcem

-0.15

.hex

-0.14

higher

-0.14

ormal

-0.14

ierz

-0.14

Ð°Ð»Ð¸Ð·Ð¸

-0.14

POSITIVE LOGITS

 cultured

0.15

 interval

0.14

 cells

0.14

 Holly

0.14

Hol

0.14

 ÄĮeskÃ¡

0.14

ember

0.14

 cell

0.14

ancell

0.14

 Plate

0.14

Activations Density 0.006%

quotation marks and symbols related to dialogue or speech

No Comments

No Known Activations