INDEX

Explanations

product names and their specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ikt

-0.14

wil

-0.14

 Kemp

-0.14

Ak

-0.13

 disin

-0.13

 Partial

-0.13

 Byte

-0.13

ieber

-0.13

PERT

-0.13

POSITIVE LOGITS

Äįet

0.16

BoxLayout

0.15

ubat

0.15

Ð¯Ðº

0.15

 actionTypes

0.14

llx

0.14

ÑĩÐµÑĤ

0.14

lla

0.14

MMdd

0.14

iona

0.14

Activations Density 0.024%

product names and their specifications

No Comments

No Known Activations