INDEX

Explanations

concepts related to navigation and organization within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

@qq

-0.18

ared

-0.17

gio

-0.16

ipse

-0.15

yled

-0.15

rier

-0.15

yle

-0.14

ARED

-0.14

ifs

-0.14

ldata

-0.14

POSITIVE LOGITS

urai

0.16

 Freed

0.16

ucci

0.15

ÑĩÑĥÐº

0.15

asaki

0.15

_Controller

0.14

 setFrame

0.14

èĪ

0.14

gen

0.14

lÃ¼

0.13

Activations Density 0.001%

concepts related to navigation and organization within a text

No Comments

No Known Activations