INDEX

Explanations

technical terms related to programming and database management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 gist

-0.17

ignon

-0.15

 curs

-0.14

ewe

-0.14

åĲ¾

-0.14

OUSE

-0.14

etti

-0.14

ships

-0.13

enzyme

-0.13

pper

-0.13

POSITIVE LOGITS

same

0.22

 same

0.20

annah

0.18

igne

0.16

classic

0.16

usual

0.15

 classic

0.15

SAME

0.15

enschaft

0.15

deme

0.15

Activations Density 0.171%

technical terms related to programming and database management

No Comments

No Known Activations