INDEX

Explanations

technical details related to timing and operational cycles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

è¡Ĺéģĵ

-0.16

isse

-0.15

okt

-0.15

ãĥ³ãĥĸ

-0.15

upa

-0.14

anchise

-0.14

luet

-0.14

ÑĩÐ¸Ðµ

-0.14

aura

-0.14

ecko

-0.14

POSITIVE LOGITS

 Giov

0.17

conde

0.17

oven

0.16

ause

0.15

VA

0.15

oleon

0.15

asc

0.15

odore

0.14

 Folk

0.14

yx

0.14

Activations Density 0.271%

technical details related to timing and operational cycles

No Comments

No Known Activations