INDEX

Explanations

references to various themes and concepts related to evaluation and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Mig

-0.16

slaught

-0.16

ekler

-0.16

Ð¾Ð·Ð´

-0.15

orex

-0.14

iyim

-0.14

itk

-0.14

uer

-0.14

strict

-0.14

roll

-0.13

POSITIVE LOGITS

 ÑĢÐ°Ð²Ð½Ð¾

0.14

åĦ

0.13

èĳ

0.13

ÙħÙĨØª

0.13

essenger

0.13

Browsable

0.12

atoria

0.12

.ls

0.12

TestId

0.12

 æģ

0.12

Activations Density 0.101%

references to various themes and concepts related to evaluation and categorization

No Comments

No Known Activations