INDEX

Explanations

references to the concept of "lore."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÑĮ

-0.17

 Hass

-0.16

ulling

-0.15

style

-0.14

arian

-0.14

agem

-0.14

rosse

-0.14

ÑĢÐ¸ÑĦ

-0.14

ilor

-0.14

ym

-0.13

POSITIVE LOGITS

chema

0.18

graf

0.16

ÑīÑĸ

0.15

umpt

0.15

-License

0.14

asar

0.14

ograf

0.14

 Liver

0.14

BAT

0.14

Ð¿ÑĸÐ´

0.14

Activations Density 0.026%

references to the concept of "lore."

No Comments

No Known Activations