INDEX

Explanations

references to logging frameworks and related programming artifacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ê¼

-0.15

Ari

-0.15

Î±Î½Î´

-0.14

arser

-0.14

Illuminate

-0.14

 gÃ©

-0.14

%A

-0.14

.vm

-0.14

POSITIVE LOGITS

bsolute

0.19

0.18

cxx

0.18

aldo

0.17

zcze

0.15

ecs

0.15

 metab

0.15

rent

0.15

upo

0.15

net

0.14

Activations Density 0.004%

references to logging frameworks and related programming artifacts

No Comments

No Known Activations