INDEX

Explanations

references to individuals and their familial or professional backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

agma

-0.15

 Reverse

-0.15

 dara

-0.14

Reverse

-0.14

Ãªn

-0.14

enso

-0.14

Ã±a

-0.14

ount

-0.14

reverse

-0.14

eller

-0.13

POSITIVE LOGITS

 parents

0.17

ibri

0.16

&view

0.15

 parent

0.14

é¼

0.14

ëĮ

0.14

.Generated

0.13

acc

0.13

_keywords

0.13

parents

0.13

Activations Density 0.044%

references to individuals and their familial or professional backgrounds

No Comments

No Known Activations