INDEX

Explanations

references to personal experiences and anecdotes

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

uner

-0.15

 anything

-0.14

dorf

-0.14

ournals

-0.14

ãģĿãĤĮ

-0.14

 ambos

-0.13

Both

-0.13

imo

-0.13

POSITIVE LOGITS

 another

0.34

 someone

0.31

 somebody

0.31

another

0.28

çļĦä¸Ģä¸ª

0.28

someone

0.26

 eines

0.23

 sebuah

0.23

our

0.23

 ÛĮÚ©ÛĮ

0.23

Activations Density 0.590%

references to personal experiences and anecdotes

No Comments

No Known Activations