INDEX

Explanations

references to web application components and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

_tD

-0.18

mlin

-0.17

_mD

-0.17

_mE

-0.15

_mC

-0.15

ÑĢÐ°Ð¶

-0.15

eldon

-0.15

jam

-0.14

qli

-0.14

nave

-0.14

POSITIVE LOGITS

tea

0.17

zano

0.15

Sha

0.15

Tea

0.15

rys

0.14

 Skyl

0.14

io

0.14

ãĥ³ãĥĨãĤ£

0.14

ruise

0.14

Usa

0.13

Activations Density 0.075%

references to web application components and structures

No Comments

No Known Activations