INDEX

Explanations

concepts related to selfishness and selflessness

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

uem

-0.16

adal

-0.15

pad

-0.15

ucket

-0.15

ixin

-0.15

ãĥĪãĥª

-0.15

Pad

-0.14

leans

-0.14

iyle

-0.14

ÙĨÙĩ

-0.14

POSITIVE LOGITS

fulness

0.16

ness

0.16

lessly

0.15

nees

0.15

nes

0.15

CADE

0.14

rious

0.14

ë®¤

0.14

Ð°ÑĢÑı

0.14

 Toll

0.14

Activations Density 0.008%

concepts related to selfishness and selflessness

No Comments

No Known Activations