INDEX

Explanations

future-oriented phrases indicating intention or planned actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ento

-0.16

 Ð½Ð°Ðº

-0.13

alty

-0.13

arf

-0.13

lobals

-0.13

cop

-0.13

 involvement

-0.13

 otur

-0.13

issa

-0.12

Īĺ

-0.12

POSITIVE LOGITS

 released

0.19

 release

0.19

 available

0.19

 exist

0.18

åŃĺåľ¨

0.18

_release

0.17

 existence

0.17

 exists

0.17

_AVAILABLE

0.16

release

0.16

Activations Density 0.170%

future-oriented phrases indicating intention or planned actions

No Comments

No Known Activations