INDEX

Explanations

references to various file types and digital formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.15

oty

-0.15

adors

-0.15

 eldre

-0.14

Nam

-0.14

 ÙħØ§Ø¯

-0.14

oric

-0.14

 Settlement

-0.14

oti

-0.14

Dod

-0.13

POSITIVE LOGITS

iosper

0.17

’Brien

0.16

egrator

0.15

ilig

0.15

 Wake

0.14

itag

0.14

Mu

0.14

 bolt

0.14

kup

0.14

 endors

0.14

Activations Density 0.029%

references to various file types and digital formats

No Comments

No Known Activations