INDEX

Explanations

terms that indicate broad or extensive relationships and opportunities across 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

sel

-0.20

sek

-0.15

 altogether

-0.14

lix

-0.14

etc

-0.14

aml

-0.14

ylvania

-0.14

å°Ĥ

-0.14

entai

-0.14

chu

-0.14

POSITIVE LOGITS

 context

0.22

anging

0.22

-scale

0.20

 picture

0.19

/general

0.18

-reaching

0.18

-ranging

0.18

 wider

0.18

-picture

0.18

 trends

0.18

Activations Density 0.031%

terms that indicate broad or extensive relationships and opportunities across various contexts

No Comments

No Known Activations