INDEX

Explanations

references to annual events and their details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

urette

-0.16

aders

-0.15

frag

-0.14

ckill

-0.14

cls

-0.14

onda

-0.14

oppable

-0.13

ctal

-0.13

ader

-0.13

undos

-0.13

POSITIVE LOGITS

chten

0.14

 xuyÃªn

0.14

eria

0.13

umen

0.13

.VideoCapture

0.13

ÐłÐ¾Ð·

0.13

 Bald

0.13

unk

0.13

izia

0.12

bod

0.12

Activations Density 0.000%

references to annual events and their details

No Comments

No Known Activations