INDEX

Explanations

technical terms and structures related to programming and databases

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

 æ¹

-0.16

Ð°Ð¼Ð°

-0.16

Rid

-0.14

yne

-0.14

ridge

-0.14

#__

-0.14

 gian

-0.13

ahun

-0.13

GetSize

-0.13

rying

-0.13

POSITIVE LOGITS

oval

0.16

reon

0.15

esome

0.15

mw

0.15

ennes

0.15

.il

0.14

orman

0.14

eload

0.14

gles

0.14

pes

0.14

Activations Density 0.267%

technical terms and structures related to programming and databases

No Comments

No Known Activations