INDEX

Explanations

references to specific products and promotional offers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

irim

-0.16

Ã©gor

-0.16

ofilm

-0.15

onymous

-0.14

edla

-0.14

formik

-0.14

idak

-0.14

sson

-0.14

ntity

-0.13

otor

-0.13

POSITIVE LOGITS

((__

0.15

ocz

0.15

 ØŃØ§ÙĦ

0.14

ìľ¼

0.14

PLIC

0.14

Ń

0.13

pike

0.13

ÙĬØ¬

0.13

ingo

0.13

Activations Density 0.228%

references to specific products and promotional offers

No Comments

No Known Activations