INDEX

Explanations

references to wounds and infections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ë´ī

-0.18

alic

-0.17

kok

-0.17

chu

-0.15

itr

-0.14

egr

-0.13

arget

-0.13

str

-0.13

olian

-0.13

/legal

-0.13

POSITIVE LOGITS

Fur

0.16

 STATES

0.15

 Mahar

0.15

 Lehr

0.15

 Mehr

0.15

nde

0.15

amenti

0.14

blade

0.14

odesk

0.14

 Timothy

0.14

Activations Density 0.135%

references to wounds and infections

No Comments

No Known Activations