INDEX

Explanations

phrases indicating options or alternatives in a discussion or argument

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ISODE

-0.15

Ø²Ùĩ

-0.15

lant

-0.15

anz

-0.14

iez

-0.14

onga

-0.14

ynet

-0.14

.GetResponse

-0.14

iesta

-0.14

rient

-0.14

POSITIVE LOGITS

or

0.17

opa

0.16

0.15

upy

0.14

 rainbow

0.14

-course

0.14

æŀ

0.14

 keyed

0.14

Activations Density 0.113%

phrases indicating options or alternatives in a discussion or argument

No Comments

No Known Activations