INDEX

Explanations

discussions about differences and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Downs

-0.15

ÅĻi

-0.15

ÐĶÐļ

-0.14

áº¯t

-0.13

ocaly

-0.13

 Doyle

-0.13

lobber

-0.13

chu

-0.13

 junto

-0.13

á»©ng

-0.13

POSITIVE LOGITS

 difference

0.92

 differences

0.85

difference

0.79

 Difference

0.77

Difference

0.73

 Differences

0.73

 diffÃ©

0.67

å·®

0.64

 differ

0.62

_difference

0.60

Activations Density 0.408%

discussions about differences and comparisons

No Comments

No Known Activations