INDEX

Explanations

mentions of contributors and organizational elements related to staff or authorship

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

 Candid

-0.15

ynet

-0.14

asser

-0.14

atic

-0.14

arie

-0.14

mani

-0.14

idia

-0.13

 tape

-0.13

sea

-0.13

 Jacobs

-0.13

POSITIVE LOGITS

strup

0.16

ìĸ¸

0.16

SCRIPTOR

0.15

Ð»Ð¸Ð²

0.15

ritch

0.15

 ngÃ´n

0.15

iegel

0.15

jdk

0.14

CommandEvent

0.14

orthand

0.14

Activations Density 0.240%

mentions of contributors and organizational elements related to staff or authorship

No Comments

No Known Activations