INDEX

Explanations

terms related to hosting and presenting in media contexts

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

tras

-0.17

imax

-0.16

 Berry

-0.15

udas

-0.15

andro

-0.15

oko

-0.15

uder

-0.14

iev

-0.14

POSITIVE LOGITS

ReadStream

0.17

MOTE

0.15

.ctrl

0.14

Å¡ov

0.14

 onRequest

0.14

 TMPro

0.13

ICS

0.13

 biliyor

0.13

formats

0.13

osaur

0.13

Activations Density 0.018%

terms related to hosting and presenting in media contexts

No Comments

No Known Activations