INDEX

Explanations

website and domain-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

uala

-0.17

Zem

-0.16

erland

-0.16

oldem

-0.15

uras

-0.15

pread

-0.14

ikon

-0.14

stoff

-0.14

Ð°Ð»Ð¾Ð²

-0.14

ÑįÑĦ

-0.14

POSITIVE LOGITS

.com

0.19

.synthetic

0.15

arness

0.15

 Sprint

0.14

ament

0.14

obr

0.14

Pragma

0.14

ajs

0.13

 snÃŃm

0.13

Rap

0.13

Activations Density 0.031%

website and domain-related terms

No Comments

No Known Activations