INDEX

Explanations

references to specific people and terms related to media, organizations, or ratings

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

à¸Ĺà¸£

-0.16

æ³¡

-0.15

ascar

-0.15

aginator

-0.15

pecific

-0.15

lectron

-0.15

_inches

-0.15

itesse

-0.15

iferay

-0.14

izzie

-0.14

POSITIVE LOGITS

adays

0.20

Ã£o

0.16

en

0.15

elt

0.15

0.14

our

0.14

ise

0.14

ern

0.14

odore

0.14

Activations Density 0.461%

references to specific people and terms related to media, organizations, or ratings

No Comments

No Known Activations