INDEX

Explanations

references to specific products or items, particularly with a focus on feelings and personal experiences related to them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

klu

-0.17

amarin

-0.16

aidu

-0.15

Ã¼ss

-0.14

 ç½

-0.14

azon

-0.14

iosper

-0.14

à¤¾à¤²à¤¤

-0.14

irit

-0.14

loat

-0.14

POSITIVE LOGITS

-Cs

0.15

ener

0.15

Î¯

0.15

Ð³Ð°Ð»Ñĸ

0.14

mes

0.14

equ

0.13

ETS

0.13

_tensors

0.13

pro

0.13

 collo

0.13

Activations Density 0.165%

references to specific products or items, particularly with a focus on feelings and personal experiences related to them

No Comments

No Known Activations