INDEX

Explanations

variations of the word "entertain" and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Intensity

-0.15

SSION

-0.15

cial

-0.15

trand

-0.15

Wunused

-0.14

ElementException

-0.14

SF

-0.14

nton

-0.14

ction

-0.14

POSITIVE LOGITS

ropic

0.25

_QUOTES

0.22

rench

0.21

ertainment

0.20

prises

0.20

angled

0.20

itled

0.18

ourage

0.16

rop

0.16

Activations Density 0.015%

variations of the word "entertain" and its related forms

No Comments

No Known Activations