INDEX

Explanations

references to academic journal articles 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 @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

eller

-0.16

mount

-0.14

;:

-0.14

Fah

-0.14

posta

-0.14

 deposit

-0.14

 Shapiro

-0.14

Sas

-0.14

traction

-0.14

eric

-0.13

POSITIVE LOGITS

ansi

0.17

utter

0.16

ftware

0.15

 Hunger

0.14

amed

0.14

Intermediate

0.14

à¹īà¸ĩ

0.14

dac

0.14

 âĸ¼

0.14

Activations Density 0.038%

references to academic journal articles and their details

No Comments

No Known Activations