INDEX

Explanations

numerical values related to research and scientific data

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

èŃ·

-0.15

ugen

-0.15

raid

-0.15

rello

-0.15

oret

-0.14

rei

-0.14

ano

-0.14

Å¾el

-0.14

umm

-0.14

reon

-0.14

POSITIVE LOGITS

0.20

jeme

0.16

0.15

eless

0.15

 Femme

0.15

arde

0.15

umeric

0.14

peare

0.14

SION

0.14

vÄĽÅĻ

0.14

Activations Density 0.057%

numerical values related to research and scientific data

No Comments

No Known Activations