INDEX

Explanations

instances of the prefix "unh" typically associated with negative connotations or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Î²Îµ

-0.17

-0.16

ourn

-0.15

ero

-0.15

ERO

-0.14

ITTER

-0.14

isy

-0.14

loit

-0.14

isphere

-0.14

idelity

-0.14

POSITIVE LOGITS

 Parker

0.17

IFA

0.17

ind

0.15

ukes

0.15

indr

0.14

MES

0.14

 hinge

0.14

IB

0.14

elib

0.14

èĻİ

0.14

Activations Density 0.018%

instances of the prefix "unh" typically associated with negative connotations or states

No Comments

No Known Activations