INDEX

Explanations

HTML and related markup elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

iets

-0.16

_INLINE

-0.16

atan

-0.15

ziej

-0.15

lake

-0.15

Ø±ÙĪØ¨

-0.15

cade

-0.14

TeX

-0.14

TabPage

-0.14

Mocks

-0.14

POSITIVE LOGITS

<head

0.23

 head

0.18

 HEAD

0.17

 Sher

0.17

da

0.15

iram

0.15

 dear

0.15

ynam

0.14

 Head

0.14

ERA

0.14

Activations Density 0.012%

HTML and related markup elements

No Comments

No Known Activations