INDEX

Explanations

words and phrases related to programming and testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

_leaf

-0.15

ENDOR

-0.15

ogl

-0.14

aval

-0.14

UIT

-0.14

å£

-0.14

 Cler

-0.14

robat

-0.14

ulg

-0.14

POSITIVE LOGITS

 Tort

0.17

 tort

0.16

 TORT

0.15

WND

0.15

porte

0.15

postalcode

0.15

itzer

0.14

PDO

0.14

ãĥ¼ãĥ©

0.14

PSD

0.14

Activations Density 0.075%

words and phrases related to programming and testing

No Comments

No Known Activations