INDEX

Explanations

conditional statements and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

.scalablytyped

-0.15

GLOBALS

-0.14

 hopefully

-0.14

aware

-0.14

 Oval

-0.14

egend

-0.14

isay

-0.14

onia

-0.14

ieÅ¼

-0.13

_vlog

-0.13

POSITIVE LOGITS

 based

0.42

 Based

0.38

based

0.34

Based

0.33

 according

0.31

 dá»±a

0.28

fit

0.27

according

0.27

 basis

0.26

æł¹æį®

0.26

Activations Density 0.004%

conditional statements and their implications

No Comments

No Known Activations

conditional statements and their implications

No Comments

No Known Activations