INDEX

Explanations

mentions of publishers and publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

TES

-0.15

neau

-0.15

ussian

-0.15

Ãºc

-0.14

opensource

-0.14

Ã§

-0.14

hesion

-0.14

áº¯n

-0.14

uers

-0.13

à¤¾à¤µ

-0.13

POSITIVE LOGITS

ogany

0.17

 Surface

0.16

ekyll

0.14

ostat

0.14

itÃł

0.14

zilla

0.14

0.13

Ã©n

0.13

PDO

0.13

Activations Density 0.071%

mentions of publishers and publication details

No Comments

No Known Activations