INDEX

Explanations

punctuation marks and their frequencies in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chwitz

-0.17

evi

-0.16

uchs

-0.16

ickt

-0.16

 meanwhile

-0.15

uggage

-0.14

ephir

-0.14

izon

-0.14

gos

-0.14

regor

-0.14

POSITIVE LOGITS

Lets

0.15

lea

0.14

á»ĵi

0.14

kov

0.14

ete

0.13

illes

0.13

 Lets

0.13

sealed

0.13

 dá»¥ng

0.13

Activations Density 0.532%

punctuation marks and their frequencies in text

No Comments

No Known Activations