INDEX

Explanations

words related to the concept of "life" or "living."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

es

-0.23

eses

-0.19

eson

-0.18

ibold

-0.18

eres

-0.18

esy

-0.17

ingt

-0.17

esa

-0.17

esch

-0.17

ijk

-0.16

POSITIVE LOGITS

0.23

alue

0.18

vy

0.16

à¥įà¤¹

0.16

elocity

0.15

erno

0.15

ALES

0.15

ariant

0.15

estro

0.15

orce

0.15

Activations Density 0.020%

words related to the concept of "life" or "living."

No Comments

No Known Activations