INDEX

Explanations

programming syntax and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 kolo

-0.16

orado

-0.16

 MyBase

-0.15

_EDEFAULT

-0.15

ampa

-0.15

Ðĭ

-0.15

akra

-0.15

auga

-0.14

ATA

-0.14

arin

-0.14

POSITIVE LOGITS

fur

0.16

ozem

0.16

 NULL

0.15

mall

0.15

curl

0.14

 free

0.14

 liberated

0.14

_SYMBOL

0.14

ãĤ«ãĥ¼ãĥī

0.14

chain

0.14

Activations Density 0.312%

programming syntax and structure

No Comments

No Known Activations