INDEX

Explanations

references to test execution and related terminology in software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ogan

-0.18

znik

-0.18

avra

-0.17

ikut

-0.16

 Stall

-0.16

Ð³Ð°Ð»

-0.16

erais

-0.16

lai

-0.16

SystemService

-0.15

baugh

-0.15

POSITIVE LOGITS

0.14

obra

0.14

op

0.14

ìĪł

0.13

 Meadows

0.13

null

0.13

sf

0.13

Activations Density 0.122%

references to test execution and related terminology in software

No Comments

No Known Activations