INDEX

Explanations

references to specific product cases and related accessories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 sweep

-0.15

 sweeps

-0.15

 swept

-0.15

ARI

-0.14

ATAB

-0.14

 anonym

-0.14

udit

-0.14

 masses

-0.14

Î´Î·

-0.14

reeze

-0.14

POSITIVE LOGITS

ä¿ĿæĬ¤

0.23

 protection

0.23

 Protection

0.23

 protector

0.23

ä¿ĿèŃ·

0.22

Protection

0.20

 protect

0.20

 scratches

0.20

Protect

0.20

protect

0.19

Activations Density 0.020%

references to specific product cases and related accessories

No Comments

No Known Activations