INDEX

Explanations

references to mentioning or talking about specific points or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

_DEFINE

-0.17

spiel

-0.15

tron

-0.15

itag

-0.15

kir

-0.15

stown

-0.15

 BirliÄŁi

-0.14

oen

-0.14

omin

-0.14

kir

-0.14

POSITIVE LOGITS

udd

0.17

Ä±rak

0.16

ecta

0.15

ulet

0.14

erdale

0.14

olley

0.14

icut

0.14

efd

0.14

imb

0.13

Activations Density 0.014%

references to mentioning or talking about specific points or subjects

No Comments

No Known Activations