INDEX

Explanations

references to directories and file paths in a computing context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

/dialog

-0.16

.appspot

-0.15

aft

-0.14

«a

-0.14

éĨ

-0.14

 Strand

-0.14

acked

-0.14

rette

-0.13

usters

-0.13

POSITIVE LOGITS

lot

0.17

Ø§Ø±Ø¬

0.14

lok

0.14

akan

0.14

monds

0.14

 Bonus

0.14

otton

0.14

Ð´ÐµÐ¼

0.13

antee

0.13

wald

0.13

Activations Density 0.044%

references to directories and file paths in a computing context

No Comments

No Known Activations