INDEX

Explanations

recommendations and suggestions for actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Î»ÎŃ

-0.14

imeo

-0.14

 Matthews

-0.14

ãģĤãģ®

-0.14

flare

-0.13

instein

-0.13

_nat

-0.13

.scal

-0.13

UILT

-0.13

beit

-0.13

POSITIVE LOGITS

0.18

/request

0.17

Ã©ri

0.17

 strongly

0.16

ahir

0.15

-es

0.15

you

0.14

 titular

0.14

fol

0.14

Activations Density 0.060%

recommendations and suggestions for actions or decisions

No Comments

No Known Activations