INDEX

Explanations

names and references to historical figures in academia

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

igon

-0.17

 Dixon

-0.15

 collateral

-0.14

(AT

-0.14

UIL

-0.14

WW

-0.14

 sitting

-0.14

uv

-0.14

xon

-0.14

ite

-0.13

POSITIVE LOGITS

LU

0.19

BU

0.17

kÃ¼

0.17

doch

0.16

kur

0.16

PU

0.16

CUS

0.16

BUM

0.15

ÅĤu

0.15

Î»Î¼

0.15

Activations Density 0.102%

names and references to historical figures in academia

No Comments

No Known Activations