INDEX

Explanations

syntactic elements and data attributes in a structured code format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

nas

-0.15

vu

-0.15

Cab

-0.14

aghetti

-0.13

 crunch

-0.13

odash

-0.13

afil

-0.13

.dex

-0.13

Histogram

-0.13

Tile

-0.13

POSITIVE LOGITS

 Tiny

0.34

 editor

0.32

Tiny

0.30

editor

0.29

tin

0.29

 tiny

0.29

(editor

0.29

 Editor

0.27

tiny

0.27

/tiny

0.27

Activations Density 0.097%

syntactic elements and data attributes in a structured code format

No Comments

No Known Activations