INDEX

Explanations

references to new additions or arrivals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

kinson

-0.16

Ð¿Ðµ

-0.15

Ķ

-0.14

ÐºÐ¾Ð²Ð¾

-0.14

 disag

-0.14

harma

-0.14

efa

-0.13

à¸Ĳ

-0.13

_EM

-0.13

POSITIVE LOGITS

 colum

0.17

Ãły

0.15

ynom

0.15

anos

0.14

(ins

0.14

Bis

0.14

bis

0.14

ANNOT

0.14

itos

0.14

sz

0.14

Activations Density 0.102%

references to new additions or arrivals

No Comments

No Known Activations