INDEX

Explanations

structured question-and-answer formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

nton

-0.16

áŁĴáŀ

-0.15

 Fucked

-0.15

iswa

-0.14

Ø²Ùĩ

-0.14

mtree

-0.14

UGHT

-0.14

-0.13

cap

-0.13

apsed

-0.13

POSITIVE LOGITS

SO

0.17

 answer

0.15

pga

0.15

emin

0.15

stackoverflow

0.15

insky

0.14

hos

0.14

©

0.14

lag

0.14

-fix

0.14

Activations Density 0.049%

structured question-and-answer formats

No Comments

No Known Activations

structured question-and-answer formats

No Comments

No Known Activations