INDEX

Explanations

occurrences of the word "of"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

lip

-0.16

ur

-0.14

uit

-0.14

at

-0.14

lam

-0.14

_restart

-0.14

iras

-0.14

ira

-0.14

irus

-0.14

abal

-0.14

POSITIVE LOGITS

 cellFor

0.16

opup

0.15

CAC

0.15

toi

0.15

deen

0.15

iyim

0.14

iap

0.14

tones

0.14

 Labour

0.14

arakter

0.14

Activations Density 0.010%

occurrences of the word "of"

No Comments

No Known Activations