INDEX

Explanations

mentions of the term "Hudson" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

amon

-0.19

Ã¤ÃŁ

-0.16

umen

-0.16

umann

-0.15

ardon

-0.15

amber

-0.15

manship

-0.14

dor

-0.14

POSITIVE LOGITS

ubu

0.17

UFFER

0.16

aina

0.15

hon

0.15

Pru

0.15

nock

0.15

oggle

0.15

ite

0.15

ovsky

0.15

hed

0.15

Activations Density 0.011%

mentions of the term "Hudson" in various contexts

No Comments

No Known Activations