INDEX

Explanations

terms related to paralysis and physical disabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

raham

-0.15

ÑģÐ¸Ñı

-0.14

à¤ĺ

-0.14

yny

-0.14

bern

-0.14

 gramm

-0.14

bre

-0.13

athers

-0.13

iagnostics

-0.13

inals

-0.13

POSITIVE LOGITS

å®¾

0.16

meli

0.16

ikal

0.16

atak

0.15

quiv

0.14

abet

0.14

VRT

0.13

ondon

0.13

ekim

0.13

Activations Density 0.014%

terms related to paralysis and physical disabilities

No Comments

No Known Activations