INDEX

Explanations

occurrences of numerical values in various contexts

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

æĸĹ

-0.15

Ð¾ÑĢÐ¾

-0.14

aneous

-0.14

ichen

-0.14

asil

-0.14

 ÃĤu

-0.14

ãĤ·ãĥ¼

-0.13

 parsers

-0.13

 ä¸ĭåįĪ

-0.13

 pudd

-0.13

POSITIVE LOGITS

sdale

0.16

.Deep

0.16

arus

0.15

-plus

0.15

odd

0.15

lech

0.15

or

0.15

odd

0.14

dale

0.14

Activations Density 0.216%

occurrences of numerical values in various contexts

No Comments

No Known Activations