INDEX

Explanations

statistics and information related to health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

neau

-0.15

 Iterable

-0.15

uge

-0.15

 promin

-0.14

Äĥ

-0.14

 Atmos

-0.14

steen

-0.14

par

-0.14

 atmosphere

-0.13

mb

-0.13

POSITIVE LOGITS

ummies

0.19

.foundation

0.18

essenger

0.17

iationException

0.15

wart

0.15

Î»Î±Î½

0.15

ivant

0.14

 Kushner

0.14

 Baghd

0.14

ARB

0.14

Activations Density 0.041%

statistics and information related to health conditions

No Comments

No Known Activations