INDEX

Explanations

references to award nominations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

icio

-0.17

EDIA

-0.15

unate

-0.15

 archit

-0.14

oley

-0.14

anio

-0.14

ÏĦÎ±ÏĤ

-0.14

.opensource

-0.14

outil

-0.13

hci

-0.13

POSITIVE LOGITS

Ð¾ÑģÑĥÐ´

0.14

 Spicer

0.14

justice

0.14

 hidden

0.14

jong

0.14

 Borg

0.13

 hand

0.13

zilla

0.13

ÐµÑĢÑĤÐ°

0.13

Activations Density 0.007%

references to award nominations

No Comments

No Known Activations