INDEX

Explanations

references to medical symptoms and diagnostic processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ucene

-0.15

StackSize

-0.14

.observable

-0.14

vary

-0.14

ÏĮ

-0.14

ostel

-0.14

 travelers

-0.14

 watchers

-0.14

isor

-0.13

_dispatcher

-0.13

POSITIVE LOGITS

anj

0.15

 staging

0.14

 visual

0.14

erule

0.14

 Mile

0.14

ivec

0.14

 FONT

0.13

 Milan

0.13

 Colbert

0.13

ÑĤÐ¸Ð¼

0.13

Activations Density 0.027%

references to medical symptoms and diagnostic processes

No Comments

No Known Activations