INDEX

Explanations

phrases indicating sales or marketing activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

æĸĻ

-0.15

Hal

-0.15

squ

-0.15

hal

-0.15

hal

-0.15

wis

-0.15

Squ

-0.15

 Kling

-0.14

 wise

-0.14

out

-0.14

POSITIVE LOGITS

istrovstvÃŃ

0.15

 Lumpur

0.15

¼

0.15

ÅĻad

0.15

 Ø¯Ø³Øª

0.14

 sÄ±

0.14

\č↵

0.14

ailability

0.14

Generation

0.14

éľ

0.14

Activations Density 0.000%

phrases indicating sales or marketing activities

No Comments

No Known Activations