INDEX

Explanations

terms related to biological and medical concepts, particularly those involving antibiotics and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

apped

-0.17

yi

-0.17

pped

-0.16

ived

-0.15

Ð°Ð¶

-0.15

overs

-0.15

NST

-0.15

apping

-0.15

yre

-0.14

ern

-0.14

POSITIVE LOGITS

ilities

0.22

ilit

0.21

ility

0.21

bery

0.19

acteria

0.19

acter

0.18

undance

0.18

iqu

0.18

bing

0.18

iotic

0.18

Activations Density 0.080%

terms related to biological and medical concepts, particularly those involving antibiotics and their properties

No Comments

No Known Activations