INDEX

Explanations

references to medical professionals, particularly doctors and physicians

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

gers

-0.17

ties

-0.17

ters

-0.16

ted

-0.16

ithe

-0.16

lish

-0.15

enser

-0.15

áº¡ng

-0.15

ulas

-0.15

cone

-0.15

POSITIVE LOGITS

/engine

0.19

/ph

0.17

ial

0.16

iginal

0.15

imd

0.14

unction

0.14

ëŀľëĵľ

0.14

à¸į

0.13

ship

0.13

åģĩ

0.13

Activations Density 0.023%

references to medical professionals, particularly doctors and physicians

No Comments

No Known Activations