INDEX

Explanations

references to game mechanics and player experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 wikipedia

-0.16

ÅĻ

-0.15

lean

-0.15

anan

-0.14

bz

-0.14

iswa

-0.14

æİ¨èĸ¦

-0.14

Å¾e

-0.14

_DISP

-0.14

 Mahm

-0.14

POSITIVE LOGITS

ÑĢÐ°Ð²Ð°

0.15

-UA

0.14

 ç¥

0.13

Std

0.13

Wow

0.13

 annunci

0.13

iores

0.13

 released

0.13

CEO

0.13

steam

0.13

Activations Density 0.063%

references to game mechanics and player experience

No Comments

No Known Activations