INDEX

Explanations

specific technical or scientific terminology related to health, safety, or diagnostics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÌĢ

-0.15

ISE

-0.14

achel

-0.14

.Throws

-0.14

ackets

-0.13

phabet

-0.13

arges

-0.13

AYS

-0.13

encion

-0.13

annes

-0.13

POSITIVE LOGITS

adium

0.18

aden

0.18

usc

0.16

_ASSUME

0.15

nia

0.15

utin

0.14

ascar

0.14

edia

0.14

 intox

0.14

usra

0.14

Activations Density 0.437%

specific technical or scientific terminology related to health, safety, or diagnostics

No Comments

No Known Activations