INDEX

Explanations

references to the word "Earth" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erglass

-0.17

kus

-0.16

ĵ¨

-0.15

egin

-0.15

kop

-0.15

ãĥ©ãĥĥãĤ¯

-0.15

sters

-0.14

_AI

-0.14

uses

-0.14

anders

-0.14

POSITIVE LOGITS

quake

0.38

worm

0.32

bound

0.31

lings

0.30

ling

0.27

qu

0.26

moving

0.23

ly

0.22

 quake

0.21

lier

0.21

Activations Density 0.018%

references to the word "Earth" and its variations

No Comments

No Known Activations