INDEX

Explanations

terms related to specific medical conditions and cancers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.17

rong

-0.16

izo

-0.16

estroy

-0.15

akis

-0.15

velle

-0.15

eing

-0.15

reib

-0.14

å·®

-0.14

ä½

-0.14

POSITIVE LOGITS

 Woodward

0.16

itas

0.14

 Guth

0.13

pulse

0.13

suit

0.13

annes

0.13

olis

0.13

âĢĮØ§ÙĦ

0.12

throp

0.12

CA

0.12

Activations Density 0.044%

terms related to specific medical conditions and cancers

No Comments

No Known Activations