INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

og

-0.15

oso

-0.15

rss

-0.15

rss

-0.14

nad

-0.14

Boo

-0.14

lessly

-0.14

ogl

-0.14

urname

-0.14

htar

-0.14

POSITIVE LOGITS

 Begin

0.17

-begin

0.16

egin

0.16

ãĢĩ

0.15

 begin

0.14

Ð¾ÑģÐ¿

0.14

begin

0.14

 begins

0.14

Activations Density 0.113%

mathematical symbols and notations

No Comments

No Known Activations