INDEX

Explanations

questions and phrasing that express inquiry or seek clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ernet

-0.18

uya

-0.18

ried

-0.16

èŃľ

-0.15

ritz

-0.15

 Nutzung

-0.15

estion

-0.14

atern

-0.14

erno

-0.14

irm

-0.13

POSITIVE LOGITS

cha

0.14

inness

0.14

rab

0.14

mites

0.14

utch

0.14

 Echo

0.14

Eis

0.13

vou

0.13

AFF

0.13

eko

0.13

Activations Density 0.032%

questions and phrasing that express inquiry or seek clarification

No Comments

No Known Activations