INDEX

Explanations

dates and numerical values associated with events or articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ress

-0.15

kel

-0.15

uple

-0.15

 Falk

-0.15

AINS

-0.15

anna

-0.15

 Lamb

-0.14

iaux

-0.14

reme

-0.14

ault

-0.13

POSITIVE LOGITS

0.18

cÃ©

0.18

onya

0.17

|:

0.16

|--

0.16

 çħ

0.16

 |↵

0.16

rego

0.16

cej

0.15

åĩĿ

0.15

Activations Density 0.059%

dates and numerical values associated with events or articles

No Comments

No Known Activations