INDEX

Explanations

terms related to professional roles and personal grooming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ignet

-0.16

ìłĪ

-0.15

.dump

-0.15

renc

-0.15

Gran

-0.15

ÅĻÃŃt

-0.15

InstantiationException

-0.15

 modne

-0.15

 Gran

-0.15

 Ãĸr

-0.14

POSITIVE LOGITS

raz

0.40

 razor

0.36

 blade

0.36

 blades

0.35

Gil

0.34

 shaving

0.34

 shave

0.33

raz

0.33

Raz

0.32

 Razor

0.31

Activations Density 0.019%

terms related to professional roles and personal grooming

No Comments

No Known Activations