INDEX

Explanations

occurrences of programming or technical terms related to structure or functions in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÐµÐ»Ð¸Ñĩ

-0.19

LOB

-0.17

iami

-0.17

meli

-0.16

 Ð³Ð¾ÑģÐ¿Ð¾Ð´Ð°ÑĢ

-0.16

istrat

-0.15

æ¥

-0.15

htdocs

-0.15

ataka

-0.15

Ã©rc

-0.15

POSITIVE LOGITS

 McMahon

0.17

ird

0.16

bef

0.15

atÄ±r

0.14

 Barb

0.14

ikh

0.14

 Noel

0.14

bite

0.13

 Bars

0.13

SKU

0.13

Activations Density 0.002%

occurrences of programming or technical terms related to structure or functions in code

No Comments

No Known Activations