INDEX

Explanations

terms related to unlocking and revealing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

esters

-0.16

inou

-0.16

ckett

-0.16

Ø±ÙĪØ²

-0.15

odore

-0.15

odor

-0.15

ä»ĺãģĳ

-0.15

ä¸įè¶³

-0.15

 uden

-0.15

inu

-0.14

POSITIVE LOGITS

ing

0.22

(Un

0.19

 mysteries

0.19

stan

0.16

ning

0.16

lings

0.15

Nested

0.15

estroy

0.15

ken

0.15

 secrets

0.15

Activations Density 0.026%

terms related to unlocking and revealing

No Comments

No Known Activations