INDEX

Explanations

variations of the word "Green."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 breeding

-0.17

iri

-0.16

amedi

-0.16

st

-0.15

ivr

-0.15

Rim

-0.14

crow

-0.14

 breed

-0.14

IRROR

-0.14

apia

-0.14

POSITIVE LOGITS

hound

0.20

viso

0.19

elda

0.17

Gre

0.17

lish

0.17

velle

0.16

inke

0.16

gre

0.15

enco

0.15

Activations Density 0.025%

variations of the word "Green."

No Comments

No Known Activations

variations of the word "Green."

No Comments

No Known Activations