INDEX

Explanations

numerical values associated with estimates and limits

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

emey

-0.18

cts

-0.14

Ãµ

-0.13

-urlencoded

-0.13

uso

-0.13

mage

-0.13

ephir

-0.13

 Trial

-0.13

º

-0.13

 missing

-0.13

POSITIVE LOGITS

éł¼

0.14

Ø§ÙĤØ¹

0.14

å¥

0.14

Item

0.13

assin

0.13

 expectations

0.13

 Ð²ÑĢÐµÐ´

0.13

oriously

0.13

optim

0.13

è¿

0.13

Activations Density 0.078%

numerical values associated with estimates and limits

No Comments

No Known Activations