INDEX

Explanations

positive descriptors or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

otyping

-0.16

 indeb

-0.15

ori

-0.15

Bid

-0.15

]){

-0.14

rez

-0.14

peaker

-0.14

umpt

-0.14

ENCH

-0.14

POSITIVE LOGITS

way

0.20

fit

0.17

.way

0.17

 indication

0.17

ulously

0.16

arend

0.15

assin

0.15

ECT

0.15

 addition

0.15

ourn

0.15

Activations Density 0.057%

positive descriptors or evaluations

No Comments

No Known Activations