INDEX

Explanations

terms related to membership in organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

etur

-0.15

dbe

-0.15

ìº

-0.14

Î´Î®

-0.14

 Wheel

-0.14

zin

-0.14

Zwe

-0.14

ister

-0.13

abet

-0.13

å§Ķ

-0.13

POSITIVE LOGITS

 membership

0.18

membership

0.16

::$_

0.16

 Membership

0.15

hood

0.14

_INITIALIZER

0.14

 member

0.14

iglia

0.14

Activations Density 0.050%

terms related to membership in organizations

No Comments

No Known Activations