INDEX

Explanations

references to a particular business or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ed

-0.15

ende

-0.14

Gil

-0.14

othermal

-0.14

Nim

-0.14

oning

-0.13

ilib

-0.13

eda

-0.13

emy

-0.13

emp

-0.13

POSITIVE LOGITS

udev

0.18

ament

0.17

sock

0.16

Ã±ana

0.15

-client

0.15

 ÄĳÃ´

0.14

aments

0.14

ibo

0.14

ÑĩÐµ

0.14

chan

0.14

Activations Density 0.010%

references to a particular business or organization

No Comments

No Known Activations