INDEX

Explanations

phrases indicating a search or inquiry for products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ady

-0.16

 lá»ĩ

-0.15

ĳ¸

-0.13

reshold

-0.13

aras

-0.13

slaught

-0.13

vn

-0.12

 torture

-0.12

ichick

-0.12

à¸§à¸Ļ

-0.12

POSITIVE LOGITS

0.17

rang

0.15

çļĦæĺ¯

0.14

.documentation

0.14

 ways

0.14

gregar

0.13

bard

0.13

ays

0.13

orrent

0.13

Activations Density 0.071%

phrases indicating a search or inquiry for products or services

No Comments

No Known Activations