INDEX

Explanations

words and phrases related to "mono" or single characteristics in various contexts

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

lessly

-0.25

fully

-0.21

-0.18

FRING

-0.17

-0.16

ters

-0.15

otr

-0.15

-0.14

atte

-0.14

åŃ£

-0.14

POSITIVE LOGITS

ville

0.16

../../../

0.15

pain

0.15

erp

0.15

OpenHelper

0.15

-ÑĤÐ¾

0.15

itored

0.14

ìĹ´

0.14

-sided

0.14

illo

0.14

Activations Density 0.052%

words and phrases related to "mono" or single characteristics in various contexts

No Comments

No Known Activations