INDEX

Explanations

references to confidentiality and anonymity in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

gne

-0.17

istr

-0.15

.opens

-0.15

 Pers

-0.15

pton

-0.15

 ocup

-0.15

fq

-0.14

fol

-0.14

iÃ³n

-0.14

ammable

-0.14

POSITIVE LOGITS

ToBounds

0.19

linkplain

0.17

Writes

0.16

 -*-č↵

0.16

morgan

0.15

.gf

0.15

LinkId

0.15

Ú©Øª

0.14

alloca

0.14

uby

0.14

Activations Density 0.278%

references to confidentiality and anonymity in discussions

No Comments

No Known Activations