INDEX

Explanations

references to publication and authorship details in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

regor

-0.19

hurst

-0.18

anje

-0.15

adir

-0.14

ccoli

-0.14

indo

-0.14

andro

-0.14

ces

-0.14

ony

-0.14

FL

-0.14

POSITIVE LOGITS

 pragma

0.15

 mÃ£

0.14

 Responsive

0.14

chter

0.14

 responsive

0.14

Å¾

0.13

ilate

0.13

noinspection

0.13

rans

0.13

 Front

0.13

Activations Density 0.068%

references to publication and authorship details in a document

No Comments

No Known Activations

references to publication and authorship details in a document

No Comments

No Known Activations