INDEX

Explanations

mathematical expressions and variables related to equations and functions

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

antan

-0.17

.PIPE

-0.16

vil

-0.16

 undermin

-0.15

ircle

-0.15

ye

-0.14

ogi

-0.14

lÃ¼

-0.14

pNet

-0.14

impse

-0.14

POSITIVE LOGITS

ijk

0.16

itler

0.16

0.15

entes

0.15

sole

0.15

 funded

0.15

paired

0.14

oho

0.14

Äįek

0.14

 Wheeler

0.14

Activations Density 0.096%

mathematical expressions and variables related to equations and functions

No Comments

No Known Activations