INDEX

Explanations

names belonging to individuals, particularly those related to film and sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

allax

-0.15

lep

-0.15

stim

-0.15

rish

-0.15

rians

-0.15

Ä±lÄ±Ã§

-0.15

letcher

-0.14

olon

-0.14

icates

-0.14

usercontent

-0.13

POSITIVE LOGITS

ne

0.23

apolis

0.21

thers

0.18

pike

0.17

ettes

0.17

TEM

0.16

hill

0.16

ette

0.16

nest

0.15

adel

0.15

Activations Density 0.012%

names belonging to individuals, particularly those related to film and sports

No Comments

No Known Activations