INDEX

Explanations

keywords related to significant elements and actions 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_weak

-0.16

oux

-0.16

angel

-0.16

dorf

-0.16

äº®

-0.15

ys

-0.14

à¸·à¹ī

-0.14

$GLOBALS

-0.14

 Ortiz

-0.14

 Garn

-0.14

POSITIVE LOGITS

reed

0.17

orex

0.17

entr

0.17

ÙĨÛĮÙĨ

0.15

prech

0.14

ook

0.14

Č

0.14

read

0.14

lopedia

0.14

umo

0.14

Activations Density 0.016%

keywords related to significant elements and actions in various contexts

No Comments

No Known Activations