INDEX

Explanations

keywords associated with products and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

eniable

-0.17

Ãłnh

-0.15

inka

-0.14

ÑĨÑĸÐ¾Ð½Ð°Ð»ÑĮ

-0.14

uÃ§

-0.14

Ã³s

-0.14

.ÎŁ

-0.14

indsay

-0.13

vÄĽdom

-0.13

.SOCK

-0.13

POSITIVE LOGITS

 Cotton

0.17

ugar

0.15

Ø³Ùĥ

0.15

alls

0.15

ered

0.14

sur

0.14

uo

0.14

 Sugar

0.14

Case

0.13

 scho

0.13

Activations Density 0.044%

keywords associated with products and services

No Comments

No Known Activations