INDEX

Explanations

proper nouns or keywords related to entertainment or media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 WHETHER

-0.16

é¨İ

-0.15

subs

-0.15

isce

-0.14

IPHER

-0.14

aire

-0.14

iaux

-0.14

ipher

-0.14

éĥİ

-0.14

ebek

-0.14

POSITIVE LOGITS

BRO

0.15

Gel

0.15

lio

0.15

vem

0.15

imeline

0.15

 Mais

0.14

bro

0.14

 defs

0.14

emez

0.14

Activations Density 0.000%

proper nouns or keywords related to entertainment or media

No Comments

No Known Activations