INDEX

Explanations

references to photography or visual imagery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

aid

-0.15

ront

-0.14

rd

-0.14

agit

-0.14

our

-0.13

eren

-0.13

cente

-0.13

CardContent

-0.13

WithEmail

-0.13

uest

-0.13

POSITIVE LOGITS

elts

0.16

0.15

ħ§

0.15

.widgets

0.15

taken

0.14

ovat

0.13

omat

0.13

hey

0.13

Activations Density 0.023%

references to photography or visual imagery

No Comments

No Known Activations