INDEX

Explanations

function words that indicate relationships or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ã¶m

-0.15

stell

-0.15

().'/

-0.14

ruise

-0.14

kening

-0.14

.store

-0.14

 Heading

-0.14

HeaderCode

-0.14

aven

-0.14

 patter

-0.14

POSITIVE LOGITS

 hole

0.15

Nam

0.15

ijd

0.14

ritz

0.14

Gir

0.14

igne

0.14

toy

0.14

 backed

0.14

idders

0.14

 Hole

0.14

Activations Density 0.000%

function words that indicate relationships or comparisons

No Comments

No Known Activations