INDEX

Explanations

technical and programming terminologies related to software usage and configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ody

-0.14

 Electro

-0.14

rupa

-0.13

vez

-0.13

cke

-0.13

{}.

-0.13

apolis

-0.13

 CONSTANTS

-0.13

Been

-0.13

POSITIVE LOGITS

|--

0.23

[--

0.23

/--

0.22

|-

0.21

(--

0.20

[-

0.19

/-

0.19

[-

0.19

=<

0.18

(--

0.18

Activations Density 0.038%

technical and programming terminologies related to software usage and configuration

No Comments

No Known Activations