INDEX

Explanations

terms related to medical conditions and biological processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

cimal

-0.15

.GetInstance

-0.15

iras

-0.14

afka

-0.14

_cm

-0.14

_Impl

-0.13

adratic

-0.13

âĢĮØ´ÙĨ

-0.13

á»«a

-0.13

avras

-0.13

POSITIVE LOGITS

alu

0.19

 hence

0.17

olor

0.16

 consequently

0.15

 ê³§

0.15

 eventually

0.15

.userInteractionEnabled

0.15

okie

0.15

 Consort

0.15

 getResult

0.15

Activations Density 0.161%

terms related to medical conditions and biological processes

No Comments

No Known Activations