INDEX

Explanations

references to a specific software and its components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

reau

-0.16

esser

-0.15

_DF

-0.14

ÙıÙĪÙĨ

-0.14

kart

-0.14

 Episodes

-0.14

ANCELED

-0.14

uyÃªn

-0.14

à¸Ńà¸ĩ

-0.14

Ð¾Ð³ÑĢÐ°Ð´

-0.14

POSITIVE LOGITS

/fr

0.15

OVE

0.14

åģı

0.14

Pir

0.14

 Willie

0.14

gri

0.14

elen

0.13

ove

0.13

ayan

0.13

Activations Density 0.023%

references to a specific software and its components

No Comments

No Known Activations