INDEX

Explanations

references to medical and health-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ì¸

-0.16

llum

-0.16

ogg

-0.15

avis

-0.15

pped

-0.14

aoke

-0.14

ump

-0.14

 denn

-0.14

áº©y

-0.14

ibern

-0.14

POSITIVE LOGITS

ughters

0.18

 Darling

0.17

IALOG

0.16

 olsa

0.15

ughter

0.15

urb

0.15

ãģªãģı

0.14

rell

0.14

puties

0.14

spell

0.14

Activations Density 1.144%

references to medical and health-related terminology

No Comments

No Known Activations