INDEX

Explanations

aspects related to criteria and factors influencing various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

vrier

-0.17

ãĤ¸ãĤª

-0.15

bourg

-0.15

orado

-0.14

elier

-0.14

ãĥªãĥ¼

-0.14

illac

-0.14

ska

-0.14

 sanct

-0.13

thren

-0.13

POSITIVE LOGITS

 such

0.20

 including

0.19

such

0.16

 INCLUDING

0.16

including

0.15

erse

0.15

 basement

0.15

 Including

0.15

åĮħæĭ¬

0.14

Activations Density 0.207%

aspects related to criteria and factors influencing various contexts

No Comments

No Known Activations