INDEX

Explanations

instances of the prefix "uns-", indicating negativity or the opposite of a quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

usercontent

-0.19

tem

-0.16

imore

-0.16

éĽĦ

-0.16

è±

-0.16

cid

-0.15

paced

-0.15

chin

-0.15

emer

-0.15

tes

-0.15

POSITIVE LOGITS

uns

0.25

Uns

0.23

uns

0.16

/un

0.15

ub

0.15

min

0.15

ork

0.15

vap

0.14

eld

0.14

Activations Density 0.009%

instances of the prefix "uns-", indicating negativity or the opposite of a quality

No Comments

No Known Activations