INDEX

Explanations

verbs indicating permission or allowance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

rome

-0.16

rien

-0.16

hra

-0.15

okus

-0.15

xbd

-0.15

olland

-0.15

ktor

-0.15

ALLOC

-0.14

"text

-0.14

ãĥ³ãĥĳ

-0.14

POSITIVE LOGITS

ola

0.14

olia

0.14

Ð·Ð½Ð°ÑĩÐ°

0.14

orney

0.14

them

0.13

éĵ¾

0.13

 ÐĲÑĢÑħ

0.13

 circumstance

0.13

 relief

0.13

ovah

0.13

Activations Density 0.064%

verbs indicating permission or allowance

No Comments

No Known Activations