INDEX

Explanations

references to the concept of "greatest" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

/accounts

-0.15

ultipart

-0.15

AsyncResult

-0.14

ystone

-0.14

TOTYPE

-0.14

eldom

-0.14

bjerg

-0.14

ÎºÎµ

-0.14

 queryInterface

-0.14

tridges

-0.14

POSITIVE LOGITS

orb

0.14

ow

0.14

åı·

0.14

sheets

0.13

-known

0.13

isos

0.13

/latest

0.13

 PlzeÅĪ

0.13

bam

0.13

Ascii

0.13

Activations Density 0.006%

references to the concept of "greatest" in various contexts

No Comments

No Known Activations