INDEX

Explanations

terms related to medical conditions and treatment aspects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Mayer

-0.15

 undermin

-0.15

emann

-0.14

iken

-0.14

ucz

-0.14

info

-0.14

urope

-0.14

esso

-0.13

ometers

-0.13

jer

-0.13

POSITIVE LOGITS

rzy

0.16

ynet

0.16

_CLI

0.15

åĢį

0.14

olson

0.14

 Nháº¥t

0.14

caler

0.13

idot

0.13

oming

0.13

ocities

0.13

Activations Density 0.118%

terms related to medical conditions and treatment aspects

No Comments

No Known Activations