INDEX

Explanations

mathematical terms and symbols used in programming or algorithm descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

antar

-0.17

 Damen

-0.15

abar

-0.14

cente

-0.14

é¤Ĭ

-0.14

Ð°ÑĤÐµÐ»ÑĮ

-0.13

Ä±sÄ±

-0.13

Convention

-0.13

aven

-0.13

_EQUALS

-0.13

POSITIVE LOGITS

anut

0.16

jong

0.15

èĪį

0.15

à¹Ħà¸Ł

0.15

atest

0.15

Ã¼tÃ¼n

0.14

Ã¶rÃ¼

0.14

Ta

0.14

-Ta

0.14

Activations Density 0.017%

mathematical terms and symbols used in programming or algorithm descriptions

No Comments

No Known Activations