INDEX

Explanations

passive constructions and descriptions of features or characteristics

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

 Ð¾ÑĤÑģÑĥÑĤÑģÑĤÐ²

-0.16

aka

-0.15

Ø´Ùħ

-0.15

 promin

-0.15

 Proc

-0.14

REQ

-0.14

ovan

-0.14

itest

-0.14

 Wilkinson

-0.14

amel

-0.14

POSITIVE LOGITS

oppable

0.17

 immune

0.15

Nap

0.15

unfinished

0.15

etz

0.14

)did

0.14

 designed

0.14

ç¡

0.14

atab

0.14

Activations Density 0.373%

passive constructions and descriptions of features or characteristics

No Comments

No Known Activations