INDEX

Explanations

instances of the word "or" and related phrases in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

es

-0.28

eer

-0.25

ey

-0.25

esi

-0.25

elo

-0.23

ego

-0.23

etti

-0.22

esz

-0.21

ek

-0.21

POSITIVE LOGITS

iginal

0.27

ourke

0.27

outines

0.23

hythm

0.22

izont

0.20

assic

0.19

occo

0.19

respond

0.19

thern

0.18

dea

0.18

Activations Density 0.066%

instances of the word "or" and related phrases in varying contexts

No Comments

No Known Activations