INDEX

Explanations

words related to medical achievements and technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

MASK

-0.15

ima

-0.15

 mask

-0.14

inh

-0.14

isle

-0.14

irit

-0.14

icens

-0.14

ajar

-0.14

pg

-0.14

 justify

-0.14

POSITIVE LOGITS

EMPLARY

0.17

amine

0.16

arine

0.16

rve

0.15

.units

0.15

osate

0.15

 Larson

0.15

oeff

0.15

 ÐĿÐ°ÑģÐµÐ»ÐµÐ½Ð¸Ðµ

0.14

rette

0.14

Activations Density 0.001%

words related to medical achievements and technologies

No Comments

No Known Activations