INDEX

Explanations

concepts related to trust and collaboration in a professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

vern

-0.16

ollar

-0.16

erin

-0.16

æ¦Ĥ

-0.15

oola

-0.15

ì§ĢëĬĶ

-0.15

_protocol

-0.14

DS

-0.14

Protocol

-0.14

POSITIVE LOGITS

 that

0.20

that

0.20

 ettÃ¤

0.18

ENA

0.16

ystack

0.16

 Å¾e

0.16

upal

0.16

caÃ§Ã£o

0.15

 Å¼e

0.15

aket

0.15

Activations Density 0.104%

concepts related to trust and collaboration in a professional context

No Comments

No Known Activations