INDEX

Explanations

references to authenticity and tangible experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

wyn

-0.15

 overall

-0.15

 habitual

-0.15

 Blank

-0.15

 Clayton

-0.14

eling

-0.14

tring

-0.14

 fort

-0.13

hus

-0.13

ernet

-0.13

POSITIVE LOGITS

 unlike

0.20

actively

0.18

 rather

0.17

Unlike

0.16

 actively

0.16

å®ŀ

0.16

Looper

0.16

-real

0.15

ÅĻÃŃd

0.15

 real

0.15

Activations Density 0.201%

references to authenticity and tangible experiences

No Comments

No Known Activations